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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15776
    Prev
    Next
    INDEX
    Explanations

    instances where a survey or study has been conducted

    oai_token-act-pair · gpt-3.5-turbo

    the word "conducted" in relation to surveys or research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loaded
    -0.71
    itching
    -0.67
    mes
    -0.65
    mere
    -0.64
    mob
    -0.64
    cube
    -0.64
    stick
    -0.64
     Leopard
    -0.64
    ebra
    -0.62
     Leilan
    -0.61
    POSITIVE LOGITS
    onduct
    0.80
    spection
    0.73
    atform
    0.72
    uations
    0.71
     weekday
    0.71
     err
    0.69
    rador
    0.69
     conducted
    0.69
    ĸļ
    0.68
    ORS
    0.66
    Activations Density 0.021%

    No Known Activations