© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32968
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations, events, and people

    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
    +0.22
    1.1%
    659
    +0.16
    0.8%
    57
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.22
    0.14
    57
    +0.16
    0.11
    213
    +0.13
    0.09
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.80
    neapolis
    -0.66
    icable
    -0.66
    entimes
    -0.65
     Cortana
    -0.63
    ilogy
    -0.63
    ãĥ¼ãĥĨ
    -0.62
     Cheong
    -0.60
    idity
    -0.59
     "$:/
    -0.57
    POSITIVE LOGITS
    ANK
    0.92
    aku
    0.90
    urt
    0.89
    LD
    0.89
    ield
    0.89
    UV
    0.88
    SS
    0.88
    ank
    0.86
    ANG
    0.86
    ahoo
    0.86
    Activations Density 8.864%

    No Known Activations