© 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. 7-RES-JB
    11. 19054
    Prev
    Next
    INDEX
    Explanations

    verbs related to surpassing or excelling in performance

    oai_token-act-pair · gpt-3.5-turbo

    action verbs and their derivatives that describe competitive situations

    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
    unal
    -0.75
    ci
    -0.70
     Seym
    -0.68
    aghan
    -0.67
    entry
    -0.63
    azel
    -0.59
    stem
    -0.59
    aley
    -0.58
    art
    -0.58
    hent
    -0.56
    POSITIVE LOGITS
    xual
    1.13
    imental
    0.77
    urations
    0.76
    ingly
    0.75
    tenance
    0.74
    uates
    0.72
    igated
    0.70
    EMENT
    0.68
    dden
    0.68
    dated
    0.67
    Activations Density 0.087%

    No Known Activations