© 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. 3-RES-JB
    11. 4113
    Prev
    Next
    INDEX
    Explanations

    words related to spices, particularly cumin

    oai_token-act-pair · gpt-3.5-turbo

    references to the spice cumin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autonomy
    -0.75
    izoph
    -0.71
     shenan
    -0.66
    cffff
    -0.63
     bargaining
    -0.62
    ERSON
    -0.58
     millennium
    -0.58
     Immunity
    -0.58
    Kings
    -0.57
     bodily
    -0.57
    POSITIVE LOGITS
    umin
    1.26
    osity
    1.21
    ous
    1.16
    ously
    1.12
    ations
    1.03
    atus
    0.98
    urnal
    0.95
    atis
    0.90
    ates
    0.90
    ographed
    0.89
    Activations Density 0.008%

    No Known Activations