© 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. 36796
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and figures in a text

    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
    +0.18
    0.8%
    393
    +0.11
    0.5%
    328
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.18
    0.15
    396
    +0.11
    0.09
    344
    +0.10
    0.15
    Negative Logits
    Reviewer
    -0.68
    rend
    -0.66
    MSN
    -0.65
    Buff
    -0.64
    ãĤ·ãĥ£
    -0.61
     Emblem
    -0.61
    agine
    -0.60
    tick
    -0.60
    DragonMagazine
    -0.60
    arist
    -0.59
    POSITIVE LOGITS
     others
    0.86
     subsequent
    0.82
     consequ
    0.81
     respectively
    0.80
     accompanying
    0.78
     versa
    0.73
     importantly
    0.72
     percent
    0.67
     corresponding
    0.66
     additional
    0.65
    Activations Density 14.830%

    No Known Activations