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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 22126
    Prev
    Next
    INDEX
    Explanations

    phrases related to meeting or not meeting expectations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations and their fulfillment

    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
     contrace
    -0.74
    etsk
    -0.67
    İĭ
    -0.66
    smoking
    -0.62
    fusc
    -0.61
    flush
    -0.58
    aves
    -0.57
    ramer
    -0.57
     navig
    -0.57
    DOWN
    -0.57
    POSITIVE LOGITS
    edly
    0.71
     adolesc
    0.69
    ouse
    0.64
    iously
    0.62
    IGHTS
    0.62
    gypt
    0.61
     Marina
    0.61
    uations
    0.60
    amia
    0.59
    iments
    0.59
    Activations Density 0.068%

    No Known Activations