© 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
    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. 16927
    Prev
    Next
    INDEX
    Explanations

    items or quantities related to food and beverages

    oai_token-act-pair · gpt-3.5-turbo

    words indicating quantities or measures of items

    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
     coron
    -0.65
     elector
    -0.65
     ancest
    -0.64
     inval
    -0.61
    inav
    -0.60
     ideologies
    -0.58
     electors
    -0.58
     intermedi
    -0.57
    poses
    -0.57
     militias
    -0.56
    POSITIVE LOGITS
     of
    1.27
     thereof
    1.21
    Of
    1.02
     Of
    0.93
    of
    0.92
    fen
    0.89
    OF
    0.85
     OF
    0.81
    glass
    0.76
     worth
    0.74
    Activations Density 0.301%

    No Known Activations