© 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. 0-RES-JB
    11. 1165
    Prev
    Next
    INDEX
    Explanations

    phrases related to military and government actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" and variations such as "an."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antioxid
    -0.86
    WHERE
    -0.75
    RESULTS
    -0.72
     ingred
    -0.71
    SPONSORED
    -0.67
    DragonMagazine
    -0.65
    PDATE
    -0.64
     corrid
    -0.64
     enthusi
    -0.63
    Balt
    -0.63
    POSITIVE LOGITS
     a
    1.31
     an
    1.15
     another
    0.94
     some
    0.84
     someone
    0.78
     something
    0.73
     the
    0.70
    ividual
    0.67
    another
    0.66
     several
    0.65
    Activations Density 0.927%

    No Known Activations