© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39841
    Prev
    Next
    INDEX
    Explanations

    URLs and specific file paths

    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
    567
    +0.02
    0.4%
    654
    +0.02
    0.4%
    461
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.02
    0.13
    284
    +0.02
    0.09
    589
    +0.02
    0.07
    Negative Logits
    kson
    -0.16
    nostic
    -0.15
    sembly
    -0.14
     Mate
    -0.14
     deduction
    -0.14
    duction
    -0.14
     motives
    -0.14
     faults
    -0.14
     Nay
    -0.14
     Phi
    -0.14
    POSITIVE LOGITS
    www
    0.20
    wcsstore
    0.20
    pmwiki
    0.20
    Documents
    0.19
    cdn
    0.19
    Internet
    0.19
    \/\/
    0.19
    çīĪ
    0.18
    Content
    0.18
    \/
    0.18
    Activations Density 7.879%

    No Known Activations