© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17126
    Prev
    Next
    INDEX
    Explanations

    pieces or parts mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to parts or components of a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Predators
    -0.79
     Monitor
    -0.67
    elsius
    -0.59
     SER
    -0.57
     Lawyers
    -0.57
     relations
    -0.56
     translator
    -0.56
     Sector
    -0.56
     chau
    -0.56
    Compare
    -0.56
    POSITIVE LOGITS
    meal
    1.47
    ngth
    1.12
     pieces
    1.07
     Pieces
    0.96
    uania
    0.92
    glass
    0.87
     piece
    0.85
    aws
    0.85
    hooting
    0.83
    umen
    0.82
    Activations Density 0.010%

    No Known Activations