© 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. 6-RES-JB
    11. 8509
    Prev
    Next
    INDEX
    Explanations

    words related to contracting diseases or other conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contracting and contract-related scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eli
    -0.82
    ocene
    -0.78
    atin
    -0.78
     GOODMAN
    -0.75
    >>>
    -0.72
    joy
    -0.70
     COURT
    -0.68
    lete
    -0.67
    ocr
    -0.66
    agy
    -0.66
    POSITIVE LOGITS
    interstitial
    0.87
    iosity
    0.76
    phrine
    0.75
    ULAR
    0.73
    ð
    0.72
     noses
    0.71
    orne
    0.70
    pants
    0.67
    seless
    0.66
    nces
    0.66
    Activations Density 0.058%

    No Known Activations