Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1151
    Prev
    Next
    INDEX
    Explanations

    adjectives describing various qualities, such as pleasantness, unpleasantness, smoothness, uselessness, foolishness, inconvenience, singularity, profoundness, courage, inhumanity, gentleness, excitement, strangeness, bravery, uncomfortableness, and beauty

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that express strong emotional or qualitative attributes

    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
    arate
    -0.75
    ONSORED
    -0.71
    arettes
    -0.71
    ;;
    -0.67
    avia
    -0.67
    ploma
    -0.67
    orthy
    -0.65
    Swe
    -0.65
    OIL
    -0.64
    utics
    -0.64
    POSITIVE LOGITS
    est
    1.35
    ness
    1.16
    liest
    1.09
     nature
    1.03
     confines
    1.01
     notion
    0.92
     spectacle
    0.86
    ities
    0.86
    hest
    0.85
    nesses
    0.83
    Activations Density 0.325%

    No Known Activations