© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 899
    Prev
    Next
    INDEX
    Explanations

    keywords related to events or gatherings, specifically meetings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of meetings and their participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yard
    -0.78
     guessed
    -0.70
    NetMessage
    -0.67
     cite
    -0.66
     coating
    -0.65
    anchez
    -0.65
    ramids
    -0.64
    Ħ¢
    -0.64
     pat
    -0.63
    _(
    -0.63
    POSITIVE LOGITS
     stakeholders
    0.94
     delegates
    0.93
     participants
    0.80
     committee
    0.79
     Congress
    0.79
     committees
    0.79
     shareholders
    0.77
     elders
    0.77
     lawmakers
    0.76
     Presidents
    0.76
    Activations Density 0.104%

    No Known Activations