© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36318
    Prev
    Next
    INDEX
    Explanations

    information related to news articles or blog posts, particularly those covering a variety of topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.30
    1.4%
    481
    +0.16
    0.8%
    750
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.30
    0.06
    481
    +0.16
    0.38
    526
    +0.11
    -0.16
    Negative Logits
     mandate
    -0.76
    mand
    -0.75
    imester
    -0.68
    CLAIM
    -0.66
    reporting
    -0.66
    pec
    -0.65
    aniel
    -0.63
    Policy
    -0.63
    Conservative
    -0.62
    tip
    -0.62
    POSITIVE LOGITS
     goodies
    1.06
     scenery
    0.96
     treasures
    0.96
     classics
    0.91
     splend
    0.87
    abilia
    0.86
     attractions
    0.86
     talents
    0.84
     firsthand
    0.82
     amazing
    0.81
    Activations Density 28.032%

    No Known Activations