© 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. 4549
    Prev
    Next
    INDEX
    Explanations

    names of individuals or possibly places

    oai_token-act-pair · gpt-3.5-turbo

    specific names or terms associated with organizations or people

    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
    subject
    -1.08
    comed
    -1.07
    bat
    -1.00
    adapt
    -0.95
    protect
    -0.95
    license
    -0.94
    occup
    -0.93
    reading
    -0.92
    credit
    -0.91
    hered
    -0.91
    POSITIVE LOGITS
     Gin
    0.91
     Bak
    0.89
     Gul
    0.88
     Tens
    0.88
     Vent
    0.87
     Ara
    0.86
     Yar
    0.85
     Bout
    0.85
     Rai
    0.83
     Ele
    0.83
    Activations Density 0.298%

    No Known Activations