© 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. 6-RES-JB
    11. 11899
    Prev
    Next
    INDEX
    Explanations

    references to the name "Brown".

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Brown

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.83
    udeau
    -0.80
    olated
    -0.80
    ITAL
    -0.78
    Lex
    -0.77
    olkien
    -0.76
    yrim
    -0.74
    DCS
    -0.72
    isSpecialOrderable
    -0.71
    adena
    -0.70
    POSITIVE LOGITS
    lee
    1.04
    ing
    0.92
    coat
    0.89
    ells
    0.88
    erton
    0.84
    horn
    0.83
    er
    0.83
    stein
    0.82
    low
    0.81
    ell
    0.80
    Activations Density 0.014%

    No Known Activations