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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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 Local
    5. 6-RES_SCL-AJT
    6. 45218
    Prev
    Next
    INDEX
    Explanations

    references to Jewish religious figures and institutions, particularly rabbis and synagogues

    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
    7
    +0.11
    0.6%
    578
    +0.09
    0.5%
    102
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.20
    326
    +0.09
    0.20
    349
    +0.08
    0.06
    Negative Logits
    umbnail
    -0.58
    swick
    -0.55
     Hurricanes
    -0.53
    xit
    -0.53
     Lima
    -0.52
    zie
    -0.50
    itives
    -0.50
     Balkans
    -0.49
    neau
    -0.49
     Tigers
    -0.49
    POSITIVE LOGITS
     rabb
    0.67
     rabbi
    0.65
     Uriel
    0.60
     Rabbi
    0.60
     Instruct
    0.59
    iflower
    0.59
     Judaism
    0.54
    ided
    0.53
    avorite
    0.52
    ׾
    0.52
    Activations Density 6.973%

    No Known Activations