© 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. 9-RES-JB
    11. 15851
    Prev
    Next
    INDEX
    Explanations

    words related to underground or hidden locations or concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "monsters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.70
    ĪĴ
    -0.63
    isconsin
    -0.59
    İ
    -0.59
     Pace
    -0.57
     indisc
    -0.57
    utes
    -0.56
    elson
    -0.56
     borrowing
    -0.56
    Ĥİ
    -0.55
    POSITIVE LOGITS
    geist
    1.41
    ranean
    1.15
    rane
    1.12
    tainment
    1.11
    rors
    1.08
    gom
    1.06
    ROR
    1.05
    flies
    1.04
    rible
    1.04
    dam
    1.01
    Activations Density 0.066%

    No Known Activations