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. 6116
    Prev
    Next
    INDEX
    Explanations

    keywords related to decision-making and accountability

    oai_token-act-pair · gpt-3.5-turbo

    references to issues, events, and concepts related to decision-making and regulation

    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
    ippers
    -0.71
     corridors
    -0.70
    ihar
    -0.69
    iencies
    -0.69
    jri
    -0.67
     Alas
    -0.67
    SPONSORED
    -0.65
    arios
    -0.64
     notebooks
    -0.64
     trophies
    -0.63
    POSITIVE LOGITS
    ogram
    0.84
    worker
    0.75
     whose
    0.65
     commits
    0.65
    abyte
    0.65
    ritic
    0.63
     or
    0.63
    uble
    0.63
    istor
    0.63
    ographed
    0.62
    Activations Density 0.514%

    No Known Activations