© 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. 39673
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases, judicial proceedings, and crime events

    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
    +0.14
    0.7%
    39
    +0.10
    0.5%
    257
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.22
    575
    +0.10
    0.19
    762
    +0.09
    0.16
    Negative Logits
    Lear
    -0.65
    ãĤ¯
    -0.64
    POR
    -0.64
    lime
    -0.63
    Nar
    -0.62
    onom
    -0.62
    pac
    -0.60
    ãĥĥãĥī
    -0.60
    ãĤ½
    -0.60
    icion
    -0.60
    POSITIVE LOGITS
    ensis
    0.71
     respectively
    0.70
     Bowen
    0.63
     supplemented
    0.57
     Source
    0.56
    agall
    0.54
    rique
    0.53
     compounded
    0.53
     Balanced
    0.53
     Primordial
    0.53
    Activations Density 4.369%

    No Known Activations