© 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. 40362
    Prev
    Next
    INDEX
    Explanations

    locations and actions in various real-life scenarios

    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
    1.3%
    640
    +0.16
    0.9%
    393
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.22
    0.17
    123
    +0.16
    0.13
    257
    +0.11
    0.11
    Negative Logits
    llor
    -0.75
     incumb
    -0.75
     endors
    -0.64
    NOW
    -0.55
     shareholders
    -0.53
    ional
    -0.52
     implemented
    -0.52
     appoint
    -0.52
     employers
    -0.51
    username
    -0.51
    POSITIVE LOGITS
     lieu
    1.03
    animate
    0.99
     accordance
    0.96
     situ
    0.92
     spite
    0.92
     vitro
    0.89
     conjunction
    0.88
     front
    0.87
    effect
    0.86
     vain
    0.85
    Activations Density 8.842%

    No Known Activations