© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 6943
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to various subjects or entities, such as homes, tokens, and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cannabin
    -0.88
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    etheless
    -0.69
    AppData
    -0.63
    ,,,,
    -0.62
     Helpful
    -0.61
    ãĤ¤ãĥĪ
    -0.61
     NCT
    -0.60
    TextColor
    -0.59
     SetTextColor
    -0.59
    POSITIVE LOGITS
     takeover
    1.13
     shootout
    0.98
     unveiling
    0.97
     outing
    0.97
    otiation
    0.96
    yssey
    0.95
     invasion
    0.93
     trip
    0.93
    ageddon
    0.93
     tour
    0.92
    Activations Density 0.945%

    No Known Activations