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. 9447
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a strong message or call to action

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "enough" and its variations, indicating a sense of finality or a plea for limits

    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
    uay
    -0.77
    afort
    -0.76
    eston
    -0.73
    mers
    -0.70
    ser
    -0.70
    uph
    -0.68
    verty
    -0.67
    ousands
    -0.65
    maid
    -0.65
    oward
    -0.62
    POSITIVE LOGITS
     madness
    0.68
     misinformation
    0.66
     anecdotal
    0.65
     ado
    0.64
     NOTICE
    0.64
     disclaim
    0.64
     straw
    0.61
     nonsense
    0.60
     complaints
    0.59
     obvious
    0.59
    Activations Density 0.035%

    No Known Activations