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. 4-RES-JB
    6. 19294
    Prev
    Next
    INDEX
    Explanations

    dates formatted like the day followed by the month name and year

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to statistical values or votes

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

    No Comments

    Negative Logits
     tremend
    -0.95
    olicy
    -0.91
    uppet
    -0.87
    atre
    -0.83
    isode
    -0.79
    orter
    -0.79
    enhagen
    -0.79
    ilitary
    -0.78
    atem
    -0.76
    andise
    -0.76
    POSITIVE LOGITS
    384
    1.26
    6666
    1.17
    th
    0.94
    07
    0.84
    650
    0.84
    340
    0.82
    06
    0.82
    36
    0.82
    66666666
    0.81
    05
    0.81
    Activations Density 0.028%

    No Known Activations