© 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. 10-RES-JB
    11. 18972
    Prev
    Next
    INDEX
    Explanations

    words related to a catastrophic event or chaotic situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ter" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etta
    -0.70
     Cooke
    -0.68
     reins
    -0.66
     1905
    -0.62
     Strauss
    -0.62
     1886
    -0.62
     Barnes
    -0.61
    yne
    -0.60
     Dillon
    -0.60
    overs
    -0.58
    POSITIVE LOGITS
    rible
    1.31
    restrial
    1.23
    rors
    1.22
    ribly
    1.13
    rified
    1.11
    mination
    1.11
    gency
    1.10
    ROR
    1.10
    ranean
    1.06
    ror
    1.04
    Activations Density 0.055%

    No Known Activations