© 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. 8-RES-JB
    11. 18594
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is confirming information or asserting correctness

    oai_token-act-pair · gpt-3.5-turbo

    phrases affirming or emphasizing correctness or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.78
    resses
    -0.70
     Flavoring
    -0.70
    gins
    -0.69
    issues
    -0.68
    mat
    -0.64
    ĸļ
    -0.62
    minist
    -0.62
    iliated
    -0.62
    gets
    -0.61
    POSITIVE LOGITS
    eous
    0.84
     fielder
    0.68
    terday
    0.65
    !,
    0.64
     smack
    0.63
    !
    0.63
    shore
    0.62
     Nare
    0.61
     winger
    0.59
    !.
    0.59
    Activations Density 0.038%

    No Known Activations