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. 3305
    Prev
    Next
    INDEX
    Explanations

    quotation exchanges between characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or speech

    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
    £ı
    -0.73
    malink
    -0.71
    ranean
    -0.71
    ateral
    -0.69
    cv
    -0.68
     Calories
    -0.67
    inas
    -0.64
    uded
    -0.64
     ensemble
    -0.61
    WT
    -0.61
    POSITIVE LOGITS
     hello
    0.71
    asia
    0.70
     '[
    0.69
     politely
    0.64
    hett
    0.64
     bye
    0.63
     '(
    0.63
    bryce
    0.63
     TAMADRA
    0.62
     hes
    0.60
    Activations Density 0.231%

    No Known Activations