© 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. 4624
    Prev
    Next
    INDEX
    Explanations

    words related to degrading or destructive actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "des" and associated terms

    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
     tipped
    -0.74
     Holmes
    -0.72
     Hastings
    -0.69
    OWS
    -0.66
    ancial
    -0.64
    STER
    -0.64
     caregivers
    -0.63
     Palmer
    -0.61
    glers
    -0.61
    DAY
    -0.60
    POSITIVE LOGITS
    ignt
    1.03
    plet
    1.02
    icc
    1.01
    ktop
    1.00
    ugar
    0.99
    ync
    0.98
    ription
    0.95
    ynchron
    0.93
    aturated
    0.92
    pell
    0.92
    Activations Density 0.011%

    No Known Activations