© 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. 36261
    Prev
    Next
    INDEX
    Explanations

    information related to technical documentation, including programming code and instructions for various technical actions

    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
    311
    +0.09
    0.7%
    152
    +0.08
    0.6%
    535
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.26
    288
    +0.08
    0.25
    464
    +0.06
    0.09
    Negative Logits
    ufact
    -0.46
    manship
    -0.43
    ————
    -0.43
    horn
    -0.43
    hall
    -0.42
    hner
    -0.42
    ktop
    -0.41
    hoff
    -0.41
    peed
    -0.41
     jour
    -0.41
    POSITIVE LOGITS
    ados
    0.52
    angular
    0.51
    eneg
    0.49
    adoes
    0.49
    adra
    0.48
    athi
    0.47
    itude
    0.46
    ained
    0.45
    iga
    0.44
    olkien
    0.44
    Activations Density 10.612%

    No Known Activations