Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 22767
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    statistical phrases related to averages and performances

    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
    phase
    -0.71
    ighter
    -0.69
    orthy
    -0.67
    lean
    -0.67
     Nou
    -0.64
    aina
    -0.61
    士
    -0.59
     syndrome
    -0.59
    andro
    -0.59
    foundland
    -0.59
    POSITIVE LOGITS
    oday
    0.82
    uates
    0.80
    imates
    0.75
    nesota
    0.73
    imate
    0.71
     temperatures
    0.69
    uated
    0.69
    icals
    0.69
    odies
    0.68
     msec
    0.67
    Activations Density 0.034%

    No Known Activations