Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7027
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government entities and significant geopolitical references

    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
    azard
    -0.58
    aples
    -0.58
    pires
    -0.57
    rocal
    -0.55
    roup
    -0.55
    nance
    -0.54
    erenn
    -0.52
    ibaba
    -0.52
    ablish
    -0.51
    merce
    -0.51
    POSITIVE LOGITS
    _.
    0.82
    ãĢĤ
    0.80
     instead
    0.78
    !.
    0.77
    .
    0.77
     anymore
    0.73
    ðŁĺ
    0.72
     ASAP
    0.71
    ?????
    0.70
    ?,
    0.69
    Activations Density 0.991%

    No Known Activations