© 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 EvalsExportsinterp-engineNEWAPI 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. 11280
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and dates

    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
    olson
    -0.78
    phal
    -0.63
    ocene
    -0.63
    pherd
    -0.62
    eger
    -0.59
    ativity
    -0.58
     reluct
    -0.58
    sen
    -0.58
    picture
    -0.58
     exha
    -0.58
    POSITIVE LOGITS
    00
    0.92
    arth
    0.77
    -+
    0.72
    ors
    0.71
    inen
    0.69
    ulse
    0.69
    raction
    0.69
    OPLE
    0.67
    iversary
    0.65
    ectomy
    0.65
    Activations Density 0.050%

    No Known Activations