© 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. 10-RES-JB
    11. 11391
    Prev
    Next
    INDEX
    Explanations

    words related to journals or written records

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "di," indicating a focus on words related to division or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.79
     totality
    -0.70
    NetMessage
    -0.69
    witz
    -0.68
    ãģĨ
    -0.65
    FUL
    -0.65
     spare
    -0.64
    lain
    -0.62
     Rudd
    -0.62
    nesday
    -0.62
    POSITIVE LOGITS
    abol
    1.46
    ocese
    1.40
    urnal
    1.27
    abolic
    1.25
    plom
    1.16
    agon
    1.11
    agram
    1.07
    adem
    1.06
    aries
    1.02
    ploma
    1.01
    Activations Density 0.012%

    No Known Activations