Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23123
    Prev
    Next
    INDEX
    Explanations

    mentions of formal agreements or decisions made by a group or organization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation or word "Cons," often relating to consumption or consumers

    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
    WOOD
    -0.77
     Meadow
    -0.73
     Hoover
    -0.69
     ECO
    -0.67
     horses
    -0.66
     Kurd
    -0.65
     calves
    -0.63
     Wast
    -0.63
     Ames
    -0.63
     Peaks
    -0.62
    POSITIVE LOGITS
    piracy
    1.37
    ervatives
    1.36
    cientious
    1.34
    ensus
    1.33
    ensual
    1.32
    idered
    1.30
    cription
    1.27
    cript
    1.25
    umers
    1.25
    istent
    1.21
    Activations Density 0.021%

    No Known Activations