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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3916
    Prev
    Next
    INDEX
    Explanations

    sentences about technology, software development, and infrastructure

    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
    +0.26
    1.5%
    566
    +0.16
    0.9%
    393
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.26
    0.18
    393
    +0.16
    0.28
    14
    +0.12
    0.12
    Negative Logits
    osate
    -0.64
    pedia
    -0.63
    ionics
    -0.60
    ossom
    -0.57
    rarily
    -0.57
     Highlights
    -0.57
    leck
    -0.57
    netflix
    -0.56
    othal
    -0.54
    rouse
    -0.53
    POSITIVE LOGITS
     aware
    0.88
     unable
    0.84
     obligated
    0.82
     supposed
    0.82
     able
    0.82
     fortunate
    0.82
    nt
    0.80
     hereby
    0.80
     obliged
    0.79
     thankful
    0.79
    Activations Density 13.510%

    No Known Activations