© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5389
    Prev
    Next
    INDEX
    Explanations

    indicators related to engine specifications and performance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.26
    0.9%
    167
    +0.19
    0.7%
    459
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.26
    0.07
    326
    +0.19
    0.09
    288
    +0.16
    0.09
    Negative Logits
    laus
    -1.33
    atana
    -1.15
     Agric
    -1.08
    istani
    -1.07
    imedia
    -1.02
    ãĤĵ
    -0.99
     Jagu
    -0.99
    jong
    -0.98
    lyak
    -0.96
    oslov
    -0.95
    POSITIVE LOGITS
     powering
    1.14
     compartment
    1.12
     braking
    1.03
     engine
    0.99
     trunk
    0.98
     powered
    0.97
     horsepower
    0.97
     ignition
    0.96
    ugal
    0.93
     operated
    0.92
    Activations Density 1.894%

    No Known Activations