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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 21777
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to news and events

    oai_token-act-pair · gpt-3.5-turbo

    the end of documents or text passages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.68
     horizont
    -0.67
    å§
    -0.67
     fert
    -0.65
    ãĥ¼ãĥĨ
    -0.64
     Seym
    -0.63
     Chero
    -0.62
     Kurd
    -0.61
    âĨij
    -0.61
     intimid
    -0.61
    POSITIVE LOGITS
    lash
    0.84
    utenberg
    0.78
    rael
    0.76
    ELF
    0.73
    weet
    0.72
    ullivan
    0.71
    hi
    0.71
    rimp
    0.71
    ourge
    0.70
    reet
    0.70
    Activations Density 0.020%

    No Known Activations