© 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. 7788
    Prev
    Next
    INDEX
    Explanations

    mentions of Slavic surnames

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of a specific name or identifier related to an individual

    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
    nard
    -0.74
    rique
    -0.74
    icity
    -0.74
    icist
    -0.72
    icals
    -0.70
    %]
    -0.70
    mort
    -0.67
    Interstitial
    -0.66
    icas
    -0.66
    icators
    -0.64
    POSITIVE LOGITS
    wi
    1.16
    pper
    1.14
    yah
    1.11
    yo
    1.07
    ye
    1.06
    y
    1.01
    pping
    0.96
    ya
    0.96
    utenant
    0.95
    ppe
    0.94
    Activations Density 0.035%

    No Known Activations