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

    Neuronpedia

    Jacobian LensNEW
    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. 20152
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of individuals, locations, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the last name "Carr"

    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
    lihood
    -0.93
     Koran
    -0.69
     deed
    -0.68
    ĪĴ
    -0.68
    EngineDebug
    -0.68
    hh
    -0.68
     mileage
    -0.66
    ī
    -0.65
    ĨĴ
    -0.64
     diligence
    -0.63
    POSITIVE LOGITS
    agher
    1.40
    illo
    1.19
    abba
    1.04
    uth
    1.01
    ieri
    0.98
    asso
    0.97
    ache
    0.92
    agin
    0.92
    atell
    0.91
    illian
    0.90
    Activations Density 0.008%

    No Known Activations