© 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. 8-RES-JB
    11. 22425
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Rock" within the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rock" in various contexts

    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
    URES
    -0.75
    unctions
    -0.73
    urers
    -0.72
     Chandra
    -0.69
    BILITIES
    -0.66
     sidx
    -0.65
     aver
    -0.65
    abet
    -0.64
    URE
    -0.64
     tampering
    -0.62
    POSITIVE LOGITS
    ledge
    1.11
    cliffe
    1.04
    castle
    1.01
    ford
    1.01
    ingham
    0.97
    well
    0.95
    estone
    0.93
    ruff
    0.92
    fort
    0.91
    ete
    0.90
    Activations Density 0.021%

    No Known Activations