© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45799
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes and symbols within text

    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
    336
    +0.11
    0.6%
    746
    +0.11
    0.6%
    447
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.11
    0.06
    364
    +0.11
    0.07
    556
    +0.09
    0.07
    Negative Logits
     highs
    -0.58
     horizont
    -0.58
    rosse
    -0.56
     breeze
    -0.56
    xual
    -0.54
     CLSID
    -0.53
     multiplying
    -0.53
     mushrooms
    -0.52
     Photoshop
    -0.51
    inations
    -0.51
    POSITIVE LOGITS
    uggets
    1.05
    guyen
    0.97
    ominated
    0.95
    ihil
    0.86
    uclear
    0.84
    erves
    0.83
    umerous
    0.83
    XT
    0.83
    ucle
    0.83
    EM
    0.82
    Activations Density 6.727%

    No Known Activations