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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 21413
    Prev
    Next
    INDEX
    Explanations

    words related to local government actions and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to a council or governing body

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Univers
    -0.71
     Ago
    -0.69
    ibaba
    -0.65
    icio
    -0.65
    kinson
    -0.64
    avez
    -0.64
    rodu
    -0.64
    lla
    -0.63
    lihood
    -0.63
    onso
    -0.62
    POSITIVE LOGITS
    members
    1.14
     council
    1.08
    member
    1.04
     councils
    0.91
    redits
    0.90
     councill
    0.85
     chiefs
    0.84
     commissioners
    0.84
    alty
    0.83
    cill
    0.83
    Activations Density 0.015%

    No Known Activations