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. 6069
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to religion and politics, specifically names related to Shah

    oai_token-act-pair · gpt-3.5-turbo

    the name "Shah" and its variations or associated 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
    anwhile
    -0.69
     Scient
    -0.68
     Wilmington
    -0.65
    ALLY
    -0.65
    icit
    -0.64
    ilater
    -0.63
    worldly
    -0.63
    ãĤī
    -0.61
    ensical
    -0.61
     paycheck
    -0.60
    POSITIVE LOGITS
    aji
    0.91
    ulk
    0.90
    olics
    0.87
    bang
    0.85
    oran
    0.84
    loo
    0.83
    ini
    0.82
    abal
    0.80
     Alam
    0.79
    wa
    0.79
    Activations Density 0.021%

    No Known Activations