© 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. 4-RES-JB
    11. 4678
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of men

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Men" in various contexts

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

    No Comments

    Negative Logits
    ENC
    -0.78
    ENCY
    -0.78
    使
    -0.73
    ITED
    -0.73
    Closure
    -0.71
    RECT
    -0.70
    RAY
    -0.69
    âĺħâĺħ
    -0.67
    REC
    -0.66
    tainment
    -0.66
    POSITIVE LOGITS
    endez
    1.28
    iscal
    1.05
    cius
    1.05
    uscript
    1.02
    ghai
    0.99
    opausal
    0.99
    ager
    0.97
    istries
    0.95
    volent
    0.95
    ogyn
    0.88
    Activations Density 0.029%

    No Known Activations