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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5524
    Prev
    Next
    INDEX
    Explanations

    instructions or conditions related to usage or configuration

    oai_token-act-pair · gpt-3.5-turbo

    certain structures and patterns in textual data, including conditions and relationships

    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
    vind
    -0.72
    jah
    -0.71
    dict
    -0.67
    OTOS
    -0.67
    rio
    -0.65
    forts
    -0.63
    acio
    -0.63
    Marcus
    -0.62
     Citiz
    -0.60
     elusive
    -0.60
    POSITIVE LOGITS
     chances
    1.02
     respectively
    0.80
     excess
    0.73
    then
    0.72
    pmwiki
    0.72
     automatically
    0.71
     bets
    0.71
     skip
    0.70
     congratulations
    0.69
     deviations
    0.69
    Activations Density 0.276%

    No Known Activations