© 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. 6217
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Michael" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the character 'ich' in various contexts

    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
     rall
    -0.79
    heed
    -0.73
     accord
    -0.68
    ¥µ
    -0.66
     Wass
    -0.65
    ctica
    -0.64
     blaze
    -0.61
     contrace
    -0.60
     Accord
    -0.58
     scorer
    -0.57
    POSITIVE LOGITS
    icago
    1.03
    rome
    1.00
    olson
    0.96
    annel
    0.93
    sen
    0.91
    keye
    0.90
    ards
    0.86
    ynski
    0.86
    mann
    0.86
    orus
    0.82
    Activations Density 0.037%

    No Known Activations