© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and operations described in a narrative format

    oai_token-act-pair · gpt-3.5-turbo

    names associated with production roles or positions in entertainment

    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
     overrun
    -0.59
     slaughter
    -0.56
     Earthquake
    -0.54
     murders
    -0.54
     lands
    -0.54
     contaminated
    -0.54
     fou
    -0.53
     physical
    -0.53
     blight
    -0.53
     foreigners
    -0.52
    POSITIVE LOGITS
    quickShipAvailable
    0.76
    autions
    0.71
    soType
    0.70
    cipled
    0.67
    ascript
    0.66
    erity
    0.60
    editor
    0.58
    Panel
    0.57
    dding
    0.57
    jee
    0.56
    Activations Density 1.350%

    No Known Activations