© 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. 20266
    Prev
    Next
    INDEX
    Explanations

    references to a session or sessions being conducted

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of sessions

    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
    actor
    -0.65
    ging
    -0.63
    kowski
    -0.62
    ullivan
    -0.61
     underdog
    -0.60
    tymology
    -0.59
    umbai
    -0.59
    warn
    -0.59
    ":"/
    -0.58
    him
    -0.58
    POSITIVE LOGITS
    ansion
    0.89
    ional
    0.85
    UAL
    0.83
     session
    0.82
    ually
    0.82
    nikov
    0.81
     sessions
    0.74
    ellen
    0.74
    alion
    0.72
    uality
    0.72
    Activations Density 0.021%

    No Known Activations