© 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. 16888
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a movie title

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Dark" in the context of specific "Dark" themed franchises or content

    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
    ciation
    -0.77
    kson
    -0.76
    uated
    -0.74
    essional
    -0.72
    PROV
    -0.71
    ILA
    -0.70
    PsyNetMessage
    -0.69
     autop
    -0.67
     AAP
    -0.66
    odcast
    -0.66
    POSITIVE LOGITS
     Horse
    0.99
    moon
    0.95
     Ages
    0.94
     Matter
    0.85
    lord
    0.83
    er
    0.83
    fall
    0.83
     Souls
    0.82
    horse
    0.82
     Horizons
    0.81
    Activations Density 0.021%

    No Known Activations