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. 6-RES-JB
    6. 19466
    Prev
    Next
    INDEX
    Explanations

    locations and actions associated with people

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving people encountering dangerous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extraord
    -0.81
     gloss
    -0.66
     precedent
    -0.64
     wink
    -0.63
     transcript
    -0.62
    stem
    -0.62
     precedence
    -0.62
    )?
    -0.61
    cia
    -0.61
     unequivocally
    -0.61
    POSITIVE LOGITS
    bernatorial
    0.77
     groceries
    0.75
     Alexandria
    0.74
     Syndicate
    0.73
     Ern
    0.67
     town
    0.65
    uberty
    0.65
    Field
    0.65
    utical
    0.64
    oaded
    0.64
    Activations Density 0.562%

    No Known Activations