© 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. 10-RES-JB
    11. 12735
    Prev
    Next
    INDEX
    Explanations

    mentions of events or discussions taking place in a meeting setting

    oai_token-act-pair · gpt-3.5-turbo

    events related to meetings or conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amput
    -0.86
    ocaust
    -0.73
    Ble
    -0.73
    DNA
    -0.71
    psons
    -0.70
     revenge
    -0.70
    metics
    -0.70
    Tes
    -0.69
     Petty
    -0.68
    renheit
    -0.68
    POSITIVE LOGITS
     attendees
    1.69
     conference
    1.51
     meetings
    1.49
     keynote
    1.46
     speakers
    1.44
    conference
    1.44
     conferences
    1.43
     convened
    1.43
     presentations
    1.42
     discussion
    1.40
    Activations Density 0.734%

    No Known Activations