© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    6. 18632
    Prev
    Next
    INDEX
    Explanations

    mentions of specific physical attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article 'a' or 'an' preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Events
    -0.89
    Own
    -0.86
    NP
    -0.84
    orders
    -0.82
    Examples
    -0.80
    names
    -0.79
     organizations
    -0.78
    tests
    -0.78
    encies
    -0.77
    events
    -0.77
    POSITIVE LOGITS
     bunch
    1.14
     piece
    1.03
     pair
    1.02
     translucent
    1.00
     rectangle
    1.00
     towel
    1.00
     handful
    0.99
     layer
    0.98
     wooden
    0.98
     rectangular
    0.97
    Activations Density 0.253%

    No Known Activations