© 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. 22568
    Prev
    Next
    INDEX
    Explanations

    terms related to the abbreviation "SE" and surrounding text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SE," likely indicating some specific terminology or reference related to Southeast Asia or other contexts involving this acronym

    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
    raviolet
    -0.70
    starter
    -0.70
    ocrats
    -0.69
    lessly
    -0.68
    gettable
    -0.68
    ierrez
    -0.66
    onom
    -0.66
    hered
    -0.65
    enegger
    -0.65
    iasis
    -0.65
    POSITIVE LOGITS
    ASON
    1.25
    VEN
    1.24
    ARCH
    1.21
    VER
    1.12
    ATTLE
    1.10
    VERS
    1.07
    SE
    1.02
    WHERE
    1.00
    PAR
    0.93
    BOOK
    0.91
    Activations Density 0.008%

    No Known Activations