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. 7683
    Prev
    Next
    INDEX
    Explanations

    URLs referencing specific websites

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web addresses in the text

    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
    ï¸ı
    -0.74
     HMS
    -0.71
     Scheme
    -0.70
     Racial
    -0.68
     Eighth
    -0.68
     Correction
    -0.66
     Principle
    -0.64
     corrective
    -0.64
     La
    -0.64
     ACTIONS
    -0.64
    POSITIVE LOGITS
    cdn
    1.09
    yp
    0.89
    amazon
    0.89
    ecd
    0.89
    /?
    0.88
    mc
    0.84
    pedia
    0.83
    biz
    0.82
    dat
    0.82
    db
    0.81
    Activations Density 0.092%

    No Known Activations