© 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. 45786
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about products, including pricing information

    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
    0.9%
    314
    +0.15
    0.6%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.22
    -0.06
    49
    +0.15
    0.11
    149
    +0.11
    0.05
    Negative Logits
     Tall
    -0.77
     Intervention
    -0.76
     htt
    -0.71
     Tid
    -0.70
     Nare
    -0.69
     Gors
    -0.69
     Stro
    -0.69
     unders
    -0.69
     Schn
    -0.68
     Pru
    -0.68
    POSITIVE LOGITS
    $$$$
    1.42
    $$
    1.33
    USD
    1.08
    150
    0.99
    100
    0.98
    HOME
    0.96
    250
    0.95
    -$
    0.94
    £
    0.94
    GOP
    0.94
    Activations Density 11.095%

    No Known Activations