© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18682
    Prev
    Next
    INDEX
    Explanations

    references to specific documents or written records

    oai_token-act-pair · gpt-3.5-turbo

    references to documents with specific lengths and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rians
    -0.86
    uve
    -0.77
    rossover
    -0.75
    region
    -0.75
    htaking
    -0.73
    ablishment
    -0.72
    utical
    -0.71
    alian
    -0.71
    lees
    -0.71
    abiding
    -0.71
    POSITIVE LOGITS
     diary
    1.46
     autobiography
    1.44
     manifesto
    1.39
     broch
    1.38
     handwritten
    1.36
     manuscript
    1.36
     memoir
    1.34
     pamphlet
    1.34
     notebook
    1.33
     booklet
    1.32
    Activations Density 0.314%

    No Known Activations