© 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. 46077
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms related to computing and programming

    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
    636
    +0.06
    0.5%
    373
    +0.06
    0.4%
    279
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.06
    0.10
    256
    +0.06
    0.07
    493
    +0.06
    0.06
    Negative Logits
    antz
    -0.47
    avorite
    -0.44
    gur
    -0.43
    apers
    -0.42
     Watt
    -0.42
    laus
    -0.42
    ktop
    -0.41
    VB
    -0.38
    VR
    -0.38
    oat
    -0.37
    POSITIVE LOGITS
     ((
    0.44
    ithmetic
    0.43
     Âł Âł
    0.43
     bang
    0.42
    Hello
    0.42
    Statement
    0.41
     Âł Âł Âł Âł
    0.39
     Skip
    0.36
     [];
    0.36
     "#
    0.36
    Activations Density 6.029%

    No Known Activations