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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1038
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and announcements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks followed by significant phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":"/
    -0.80
    ens
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    Submit
    -0.66
    reated
    -0.66
    cia
    -0.63
    ensor
    -0.62
    ensible
    -0.62
    adr
    -0.61
    Afee
    -0.60
    POSITIVE LOGITS
     whereas
    1.40
     respectively
    1.19
     versus
    1.05
     but
    1.03
     while
    0.98
     followed
    0.97
     plus
    0.95
     etc
    0.92
     thereby
    0.89
    while
    0.86
    Activations Density 0.581%

    No Known Activations