© 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. 7-RES-JB
    11. 22579
    Prev
    Next
    INDEX
    Explanations

    instances where items in a list are separated by periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey finality or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tesy
    -0.83
    isphere
    -0.69
    lam
    -0.69
     estim
    -0.67
     exclusively
    -0.66
    onding
    -0.64
    ema
    -0.63
    nen
    -0.63
    iber
    -0.62
    ascus
    -0.62
    POSITIVE LOGITS
     Whatever
    1.10
     And
    1.09
     Worse
    1.00
     Anything
    0.99
     Repeat
    0.98
     Whoever
    0.98
     Nothing
    0.98
     Everywhere
    0.97
     Everything
    0.96
     Every
    0.96
    Activations Density 0.459%

    No Known Activations