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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15073
    Prev
    Next
    INDEX
    Explanations

    words related to graphical representations or graphs in a mathematical context

    oai_token-act-pair · gpt-3.5-turbo

    references to graphs and graphical representations

    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
    FUL
    -0.73
     tradem
    -0.69
     presumptive
    -0.67
    mediated
    -0.66
     Liberties
    -0.66
     charity
    -0.63
     Knock
    -0.61
    birth
    -0.61
    uders
    -0.60
    spoken
    -0.60
    POSITIVE LOGITS
    ically
    1.12
    alogy
    0.92
    iq
    0.89
     graph
    0.89
    graph
    0.82
     graphs
    0.82
    ql
    0.80
    ynt
    0.79
     resil
    0.77
    iewicz
    0.75
    Activations Density 0.017%

    No Known Activations