© 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. 8-RES-JB
    11. 6295
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, likely related to a person or character named "Maddow."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    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
    cles
    -0.93
    gered
    -0.72
     Skydragon
    -0.71
    ccording
    -0.68
    ASED
    -0.65
    oldown
    -0.65
    cled
    -0.64
    20439
    -0.63
    phones
    -0.62
    ãĥĩãĤ£
    -0.60
    POSITIVE LOGITS
    olf
    0.88
    olph
    0.86
    aniel
    0.86
    arius
    0.85
    uran
    0.84
    inson
    0.84
    ion
    0.84
    een
    0.83
    onis
    0.83
    ym
    0.83
    Activations Density 0.072%

    No Known Activations