© 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. 35729
    Prev
    Next
    INDEX
    Explanations

    phrases related to information management and record-keeping

    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
    393
    +0.11
    0.8%
    36
    +0.10
    0.8%
    365
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.11
    0.37
    159
    +0.10
    0.17
    263
    +0.07
    0.16
    Negative Logits
    upon
    -0.46
    lins
    -0.45
    !/
    -0.44
    agents
    -0.44
    oons
    -0.44
    ons
    -0.41
     entrants
    -0.41
    iev
    -0.41
     circumstances
    -0.40
    mes
    -0.40
    POSITIVE LOGITS
     lot
    0.57
     handful
    0.56
     sizeable
    0.56
     sizable
    0.56
     steady
    0.55
     bunch
    0.55
     foothold
    0.53
     secret
    0.51
     couple
    0.51
     vigil
    0.49
    Activations Density 5.850%

    No Known Activations