© 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. 4-RES-JB
    11. 14840
    Prev
    Next
    INDEX
    Explanations

    names related to politics and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Paul Manafort

    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
    RAL
    -0.73
    ALE
    -0.72
    CAST
    -0.72
     à¨
    -0.71
    ĪĴ
    -0.71
    ĸļ
    -0.70
    RD
    -0.70
    @#&
    -0.70
    ä¸ī
    -0.66
    NESS
    -0.65
    POSITIVE LOGITS
    afort
    1.24
     Manafort
    1.07
    uchin
    0.85
    ossier
    0.78
    umenthal
    0.76
    iola
    0.76
     indicted
    0.74
     aide
    0.73
     confid
    0.73
    andowski
    0.71
    Activations Density 0.006%

    No Known Activations