© 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. 3869
    Prev
    Next
    INDEX
    Explanations

    locations or structures, specifically focusing on castles

    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
    99
    +0.28
    1.0%
    288
    +0.27
    0.9%
    326
    +0.22
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.16
    99
    +0.27
    0.11
    326
    +0.22
    0.11
    Negative Logits
    LER
    -0.93
    uel
    -0.91
    yon
    -0.91
    ential
    -0.90
    consumer
    -0.89
    ACTED
    -0.88
    aneous
    -0.86
    nesota
    -0.85
    lass
    -0.84
    sports
    -0.84
    POSITIVE LOGITS
     decoration
    1.07
    yard
    1.06
     Dwell
    1.05
    stead
    1.05
     perched
    1.02
    lain
    1.01
     dwelling
    1.00
     dwell
    1.00
    pole
    0.99
     builder
    0.99
    Activations Density 1.800%

    No Known Activations