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. 1-RES-JB
    6. 19881
    Prev
    Next
    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    time-related markers and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.92
    merce
    -0.87
    anooga
    -0.87
    ifully
    -0.86
    iciary
    -0.80
    puter
    -0.79
    chwitz
    -0.79
    ileaks
    -0.78
    ãĤ¡
    -0.78
     nomine
    -0.78
    POSITIVE LOGITS
    92
    1.05
    91
    1.04
    82
    1.03
    81
    1.02
    34
    1.00
    83
    0.99
    12
    0.98
    02
    0.98
    85
    0.98
    03
    0.98
    Activations Density 0.037%

    No Known Activations