© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    details and descriptions related to trains, their operations, incidents involving trains, and passenger experiences on trains

    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
    +0.22
    0.8%
    385
    +0.19
    0.7%
    275
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.11
    537
    +0.19
    0.07
    325
    +0.13
    0.07
    Negative Logits
     Ambrose
    -0.98
    laus
    -0.97
     Holder
    -0.92
    erenn
    -0.89
     alien
    -0.86
    racuse
    -0.86
    berra
    -0.84
     Hague
    -0.84
    osi
    -0.83
     Kinnikuman
    -0.83
    POSITIVE LOGITS
    roads
    1.64
     conductor
    1.28
    ways
    1.25
     trains
    1.23
    cars
    1.17
    wreck
    1.16
    Train
    1.11
    tracks
    1.09
     Transit
    1.08
     derail
    1.07
    Activations Density 1.761%

    No Known Activations