© 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. 3-RES-JB
    11. 9414
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to various "Hat" characters or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -1.04
    ngth
    -1.02
     confir
    -0.82
    hower
    -0.82
     glutamate
    -0.79
    etheless
    -0.77
    ournal
    -0.77
    ¥ŀ
    -0.76
    ĸļ
    -0.73
     UNIVERS
    -0.72
    POSITIVE LOGITS
    chet
    1.12
    chery
    1.06
    Hat
    0.87
    ches
    0.86
     Hat
    0.86
    cher
    0.83
    dar
    0.83
    red
    0.82
    ched
    0.76
    rack
    0.75
    Activations Density 0.006%

    No Known Activations