© 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. 0-RES-JB
    11. 15680
    Prev
    Next
    INDEX
    Explanations

    Japanese kanji characters

    oai_token-act-pair · gpt-3.5-turbo

    specific repeated characters or symbols associated with titles or names

    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
     CLA
    -0.77
     BLM
    -0.76
     DK
    -0.74
     GM
    -0.73
     google
    -0.70
     MF
    -0.68
     LA
    -0.68
     DG
    -0.67
     Vegas
    -0.67
     DPR
    -0.66
    POSITIVE LOGITS
    Åį
    4.11
    Å«
    2.73
    Äĵ
    2.37
    Äģ
    2.16
    Ä«
    2.12
    ô
    1.92
    Ç
    1.47
    û
    1.36
    oku
    1.30
    É
    1.27
    Activations Density 0.014%

    No Known Activations