© 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. 17121
    Prev
    Next
    INDEX
    Explanations

    keywords related to streaming content or services

    oai_token-act-pair · gpt-3.5-turbo

    mentions of streaming-related content or services

    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
     misunderstanding
    -0.69
    chy
    -0.66
     Malt
    -0.64
     reluct
    -0.63
     Lat
    -0.63
    ean
    -0.63
    rpm
    -0.62
     unnecess
    -0.60
    nces
    -0.60
    unta
    -0.60
    POSITIVE LOGITS
    lining
    1.15
    stream
    1.01
     Stream
    1.00
     streams
    0.93
     stream
    0.90
    embed
    0.87
    Stream
    0.85
    liner
    0.85
    lined
    0.84
    lines
    0.81
    Activations Density 0.009%

    No Known Activations