© 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. 11714
    Prev
    Next
    INDEX
    Explanations

    instances of words related to medical procedures involving the body like surgeries or examinations

    oai_token-act-pair · gpt-3.5-turbo

    past participle forms of verbs

    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
    adra
    -0.63
    Pers
    -0.62
    rouse
    -0.60
    MAT
    -0.60
    ffield
    -0.60
    pport
    -0.60
    emet
    -0.59
    Commission
    -0.57
    ãģį
    -0.56
    izoph
    -0.56
    POSITIVE LOGITS
     by
    0.96
    aneously
    0.91
     BY
    0.84
    urally
    0.82
     into
    0.82
    onite
    0.80
     onto
    0.78
    dit
    0.74
     anew
    0.74
    uries
    0.70
    Activations Density 0.286%

    No Known Activations