© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 7331
    Prev
    Next
    INDEX
    Explanations

    quotes or reported speech preceded by "had this to say" or a similar phrase

    oai_token-act-pair · gpt-3.5-turbo

    references to conversations or statements made by individuals

    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
    icons
    -0.73
    pection
    -0.70
     INCLUD
    -0.69
    orpor
    -0.68
    idae
    -0.68
    includes
    -0.66
    omp
    -0.65
    wcs
    -0.65
     Heist
    -0.63
    "},{"
    -0.62
    POSITIVE LOGITS
     paraph
    0.97
     aloud
    0.97
     whispered
    0.91
     sarcast
    0.87
     interviewer
    0.87
     incred
    0.84
     myself
    0.83
     tweeted
    0.83
     conversation
    0.82
     uttered
    0.82
    Activations Density 0.575%

    No Known Activations