© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6326
    Prev
    Next
    INDEX
    Explanations

    official website names

    oai_token-act-pair · gpt-3.5-turbo

    references to official websites or sites related to various games or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stro
    -0.77
    hes
    -0.69
     strokes
    -0.68
    gaard
    -0.66
    entimes
    -0.66
     skew
    -0.65
    ase
    -0.64
     transpl
    -0.63
     chunk
    -0.61
     brist
    -0.61
    POSITIVE LOGITS
     Official
    3.79
    Official
    2.35
     OFFIC
    1.79
    official
    1.76
     Offic
    1.65
     official
    1.58
     Officials
    1.48
    offic
    1.31
    Offic
    1.29
     unofficial
    1.29
    Activations Density 0.015%

    No Known Activations