© 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. 45968
    Prev
    Next
    INDEX
    Explanations

    individuals with leadership roles and positions of authority in various organizations and institutions

    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
    +0.19
    0.9%
    167
    +0.13
    0.6%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.19
    0.08
    167
    +0.13
    -0.03
    93
    +0.10
    0.05
    Negative Logits
     IMAGES
    -0.75
     suscept
    -0.66
     tolerance
    -0.62
     Apocalypse
    -0.59
     Ultron
    -0.56
    asca
    -0.55
    uder
    -0.54
     susceptibility
    -0.54
     DATA
    -0.53
     kindness
    -0.53
    POSITIVE LOGITS
    woman
    1.18
    person
    1.17
    manship
    1.09
    lift
    1.07
    chair
    1.05
     chair
    1.04
    mans
    1.03
    holder
    0.94
    men
    0.92
    boards
    0.91
    Activations Density 5.978%

    No Known Activations