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. 8-RES-JB
    6. 19440
    Prev
    Next
    INDEX
    Explanations

    mentions of academic studies and reports

    oai_token-act-pair · gpt-3.5-turbo

    references to research studies and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.69
    something
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
     Sabha
    -0.62
     Alexandria
    -0.60
     predicament
    -0.58
     Rutherford
    -0.58
     Asgard
    -0.58
    mma
    -0.58
     Revival
    -0.57
    POSITIVE LOGITS
    uggest
    1.47
    hips
    1.06
    hops
    1.05
    hare
    0.99
    creen
    0.98
    mith
    0.98
    poons
    0.95
     indicate
    0.93
    chool
    0.93
    amples
    0.93
    Activations Density 0.328%

    No Known Activations