© 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. 11-RES-JB
    11. 14537
    Prev
    Next
    INDEX
    Explanations

    reports of animal sightings and events

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to incidents or reports involving wildlife

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IRA
    -0.73
     Ide
    -0.73
     Intellectual
    -0.72
     democracies
    -0.72
    Revolution
    -0.71
     Mathematics
    -0.71
     Aerospace
    -0.69
    íķ
    -0.69
     Feminist
    -0.68
    Iran
    -0.68
    POSITIVE LOGITS
     animals
    1.55
     euth
    1.53
     animal
    1.48
     veterin
    1.45
     carc
    1.40
     veterinarian
    1.39
     zoo
    1.38
     wildlife
    1.35
     deer
    1.35
     Wildlife
    1.31
    Activations Density 0.412%

    No Known Activations