© 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. 0-RES-JB
    6. 20384
    Prev
    Next
    INDEX
    Explanations

    extractions or segments from texts

    oai_token-act-pair · gpt-3.5-turbo

    references to excerpts and snippets from various texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noses
    -0.68
     cakes
    -0.64
     sockets
    -0.63
    CI
    -0.63
     tanks
    -0.62
     valve
    -0.62
     nose
    -0.61
     permanent
    -0.61
    ru
    -0.60
    KY
    -0.60
    POSITIVE LOGITS
     excerpt
    3.52
     excerpts
    2.95
    cerpt
    2.53
     snippet
    1.88
     paraph
    1.74
     snippets
    1.57
     extracts
    1.48
     transcript
    1.46
     reprinted
    1.41
     quote
    1.38
    Activations Density 0.017%

    No Known Activations