© 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. 45729
    Prev
    Next
    INDEX
    Explanations

    words related to evaluating options, considerations, and making decisions

    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
    27
    +0.16
    0.6%
    167
    +0.14
    0.5%
    68
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.16
    0.08
    702
    +0.14
    0.07
    68
    +0.11
    0.03
    Negative Logits
    ahime
    -0.83
    employment
    -0.80
    claimed
    -0.79
    etheless
    -0.79
    esan
    -0.79
    zynski
    -0.76
    ellen
    -0.75
    interrupted
    -0.74
     Leilan
    -0.74
    gradation
    -0.74
    POSITIVE LOGITS
     weigh
    1.30
     weights
    1.06
     weighing
    1.04
    ighed
    0.98
     weighed
    0.92
    iless
    0.87
     weighs
    0.85
     burdens
    0.81
     heaviest
    0.81
     pedals
    0.80
    Activations Density 6.700%

    No Known Activations