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. 2326
    Prev
    Next
    INDEX
    Explanations

    references to official press releases

    oai_token-act-pair · gpt-3.5-turbo

    instances of press releases

    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
    audi
    -0.70
    vag
    -0.69
    skill
    -0.67
     Bastard
    -0.66
     pract
    -0.66
    tsky
    -0.62
    bat
    -0.62
    structed
    -0.61
    roo
    -0.61
    otin
    -0.60
    POSITIVE LOGITS
     announcing
    1.08
     issued
    0.96
     touting
    0.81
     emailed
    0.77
     statement
    0.74
     detailing
    0.74
     titled
    0.70
     summarizes
    0.69
     disclosing
    0.68
     Regarding
    0.67
    Activations Density 0.036%

    No Known Activations