© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 19970
    Prev
    Next
    INDEX
    Explanations

    words related to graphs and graph theory

    oai_token-act-pair · gpt-3.5-turbo

    references to graphs or graphical representations

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

    No Comments

    Negative Logits
     tradem
    -0.70
    aneous
    -0.67
    NESS
    -0.66
    uders
    -0.66
    nuts
    -0.65
    ONT
    -0.63
    WHERE
    -0.63
    rican
    -0.62
    FUL
    -0.62
    ishops
    -0.62
    POSITIVE LOGITS
    ically
    1.13
    ical
    0.97
    iq
    0.86
    ql
    0.86
    ynt
    0.84
    QL
    0.82
    alogy
    0.81
    ues
    0.77
    graph
    0.77
    ician
    0.76
    Activations Density 0.010%

    No Known Activations