Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 4747
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious rituals and cultural practices

    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
    174
    +0.13
    0.5%
    288
    +0.13
    0.5%
    524
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.10
    701
    +0.13
    0.07
    174
    +0.11
    0.08
    Negative Logits
    STON
    -0.86
     Rove
    -0.83
     GOT
    -0.81
     Dayton
    -0.78
     Hoff
    -0.78
    afort
    -0.77
    Marsh
    -0.76
    lund
    -0.75
    SON
    -0.74
     skelet
    -0.72
    POSITIVE LOGITS
    isma
    0.94
    qi
    0.90
     etiquette
    0.89
    heit
    0.85
     recite
    0.84
    ensis
    0.83
    atra
    0.82
     bullshit
    0.81
    umbai
    0.78
    thood
    0.78
    Activations Density 1.838%

    No Known Activations