© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names, especially "Chuck."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Chuck."

    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
    worldly
    -0.82
    ĺħ
    -0.80
    omorphic
    -0.76
     anten
    -0.70
     circ
    -0.66
    haps
    -0.66
    ODUCT
    -0.64
    istic
    -0.64
    perse
    -0.63
     concentration
    -0.63
    POSITIVE LOGITS
    anut
    1.08
    wagon
    1.06
     Grassley
    1.02
     Schumer
    1.01
     Norris
    0.98
    bowl
    0.95
    ronics
    0.90
    tail
    0.89
    meat
    0.87
    lins
    0.83
    Activations Density 0.022%

    No Known Activations