© 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. 10-RES-JB
    11. 6671
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing approval or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dunno
    -0.82
     crap
    -0.73
     nodd
    -0.72
     shit
    -0.69
     booze
    -0.67
    sort
    -0.66
     lol
    -0.65
     gul
    -0.65
     forgot
    -0.64
    ?).
    -0.64
    POSITIVE LOGITS
     Cosponsors
    0.89
     unres
    0.77
     Members
    0.71
     strongly
    0.71
     ourselves
    0.71
     assurances
    0.70
     Chancellor
    0.69
    orough
    0.67
     Secretary
    0.67
     unequivocally
    0.65
    Activations Density 0.217%

    No Known Activations