© 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. 34731
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting information, feedback, and issues

    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
    447
    +0.17
    0.9%
    628
    +0.10
    0.5%
    196
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.37
    330
    +0.10
    0.09
    283
    +0.09
    -0.03
    Negative Logits
    ç¥ŀ
    -0.57
     challeng
    -0.52
    agall
    -0.51
     toast
    -0.49
    wark
    -0.49
    Termin
    -0.49
     booted
    -0.49
    amiya
    -0.49
    eter
    -0.48
     capped
    -0.47
    POSITIVE LOGITS
     sightings
    0.72
    ewitness
    0.63
     Household
    0.59
    è¦ļéĨĴ
    0.58
    DERR
    0.56
     Illegal
    0.55
     missing
    0.54
     omission
    0.53
     Deaths
    0.53
    ribune
    0.53
    Activations Density 21.127%

    No Known Activations