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. 9-RES-JB
    6. 13072
    Prev
    Next
    INDEX
    Explanations

    positive emotional reactions and opinions expressed in text

    oai_token-act-pair · gpt-3.5-turbo

    references to responses, feelings, and outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iliated
    -0.67
    asio
    -0.63
     urgent
    -0.62
    igate
    -0.62
    Registered
    -0.60
    integer
    -0.58
     desired
    -0.54
     starred
    -0.54
    URA
    -0.53
    untarily
    -0.53
    POSITIVE LOGITS
     antics
    0.85
     anymore
    0.82
     tho
    0.75
     being
    0.73
    _.
    0.72
    manship
    0.72
     outcome
    0.71
    comings
    0.70
     arrang
    0.69
     portrayal
    0.69
    Activations Density 0.619%

    No Known Activations