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. 3668
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a strong degree or quality of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "rather" in various contexts indicating a degree of emphasis or comparison

    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
    elsen
    -1.01
    iliate
    -0.88
    adium
    -0.84
    amba
    -0.84
    esi
    -0.82
    ividual
    -0.81
    wana
    -0.78
    Reviewed
    -0.77
    eland
    -0.75
    ulkan
    -0.75
    POSITIVE LOGITS
     amusing
    1.02
     unpleasant
    0.98
     inconvenient
    0.97
     rude
    0.92
     pointless
    0.91
     pathetic
    0.90
     nifty
    0.89
     unrem
    0.88
     unusual
    0.87
     awkward
    0.86
    Activations Density 0.020%

    No Known Activations