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. 9-RES-JB
    6. 21315
    Prev
    Next
    INDEX
    Explanations

    references to the publication "Rolling Stone."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Rolling Stone" and "zip" codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.83
    acters
    -0.79
    lower
    -0.72
    ishment
    -0.70
    erence
    -0.70
    ites
    -0.70
     hereafter
    -0.69
    ior
    -0.67
    iling
    -0.67
    ership
    -0.67
    POSITIVE LOGITS
    etheus
    0.76
    ublic
    0.73
    adoes
    0.68
    code
    0.66
    codes
    0.64
    fit
    0.64
     Tide
    0.64
    aways
    0.63
    bie
    0.62
     dancers
    0.62
    Activations Density 0.108%

    No Known Activations