© 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. 6-RES-JB
    11. 20237
    Prev
    Next
    INDEX
    Explanations

    emotional or surprising reactions in text

    oai_token-act-pair · gpt-3.5-turbo

    words that express surprise, interest, or strong reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rapp
    -0.68
    ©¶æ
    -0.64
     outage
    -0.63
    itars
    -0.62
    glas
    -0.62
    ynski
    -0.62
     sequ
    -0.61
    uben
    -0.61
    itled
    -0.61
    porary
    -0.60
    POSITIVE LOGITS
    ingly
    1.08
     him
    1.00
     us
    0.98
     onlook
    0.97
     me
    0.94
     passers
    0.92
     readers
    0.86
     listeners
    0.83
     superiors
    0.83
     audiences
    0.82
    Activations Density 0.215%

    No Known Activations