© 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. 7-RES-JB
    11. 20880
    Prev
    Next
    INDEX
    Explanations

    mentions of different animals, particularly rhinos

    oai_token-act-pair · gpt-3.5-turbo

    terms related to endangered species and wildlife conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undone
    -0.73
    isSpecialOrderable
    -0.70
    Offline
    -0.69
    iator
    -0.69
    inline
    -0.68
    mble
    -0.68
    cipled
    -0.67
    farious
    -0.66
    nce
    -0.64
    tg
    -0.64
    POSITIVE LOGITS
     species
    1.01
     carc
    0.99
     habitat
    0.98
     genus
    0.94
     populations
    0.92
     larvae
    0.92
     pup
    0.91
     biologists
    0.90
     calf
    0.88
     breeding
    0.87
    Activations Density 0.188%

    No Known Activations