© 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. 9-RES-JB
    11. 8792
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases and expressions related to decisiveness and insight

    oai_token-act-pair · gpt-3.5-turbo

    idiomatic expressions and metaphors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lav
    -0.82
    amaru
    -0.77
    Gam
    -0.71
    arov
    -0.68
    azel
    -0.68
    endar
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.66
    Sah
    -0.65
    ãĥ´ãĤ¡
    -0.65
    yond
    -0.64
    POSITIVE LOGITS
     financially
    0.83
     offensively
    0.82
     regarding
    0.67
     defensively
    0.67
     academ
    0.66
     athlet
    0.65
     emotionally
    0.64
     economically
    0.63
     bandwagon
    0.63
     ¯
    0.62
    Activations Density 0.605%

    No Known Activations