© 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. 10150
    Prev
    Next
    INDEX
    Explanations

    words that are specified by their spelling, pronunciation, or writing conventions

    oai_token-act-pair · gpt-3.5-turbo

    instances of spelling, unique identifiers, and code syntax

    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
    reenshots
    -0.74
    Tokens
    -0.72
    SPONSORED
    -0.69
    reviewed
    -0.68
    ometers
    -0.68
    Notable
    -0.66
    astern
    -0.66
    absor
    -0.65
    rites
    -0.64
    arching
    -0.64
    POSITIVE LOGITS
     "_
    1.36
     "-
    1.34
     "#
    1.33
     "(
    1.32
     "@
    1.32
     "$
    1.28
     ".
    1.26
     "+
    1.25
     "\
    1.25
     "/
    1.22
    Activations Density 0.270%

    No Known Activations