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. 18346
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "wrong"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating errors or failures

    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
    gil
    -0.77
    ecd
    -0.70
    prise
    -0.70
    resent
    -0.69
    ocry
    -0.69
    weekly
    -0.68
    Portland
    -0.66
    cit
    -0.66
    otine
    -0.66
    urst
    -0.66
    POSITIVE LOGITS
     havoc
    0.75
     unexpectedly
    0.67
     miser
    0.65
     horribly
    0.64
     onstage
    0.64
     Oops
    0.63
    aneously
    0.62
     during
    0.62
     catast
    0.61
    eria
    0.61
    Activations Density 0.039%

    No Known Activations