© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 12342
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the surname "Norquist" or "Strom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bulg
    -0.78
    jack
    -0.66
     Sussex
    -0.63
    WARD
    -0.63
     Cork
    -0.62
     Grid
    -0.61
     Memphis
    -0.61
     HIP
    -0.60
     logical
    -0.60
     Maurit
    -0.60
    POSITIVE LOGITS
    quist
    1.51
    gren
    1.21
    strom
    1.00
    ensen
    0.93
    thal
    0.88
    atures
    0.87
    qv
    0.85
    inav
    0.85
    inez
    0.85
    mann
    0.85
    Activations Density 0.007%

    No Known Activations