© 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. 20637
    Prev
    Next
    INDEX
    Explanations

    forms of text regarding copyright information or terms of use

    oai_token-act-pair · gpt-3.5-turbo

    regulations regarding the distribution and use of written materials

    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
    alach
    -0.55
    amina
    -0.54
     SetTextColor
    -0.52
    uku
    -0.52
    abe
    -0.51
     actionGroup
    -0.50
     Iw
    -0.49
    dan
    -0.49
    milo
    -0.48
    Gi
    -0.48
    POSITIVE LOGITS
    ãĥ³ãĤ¸
    0.63
     toile
    0.60
    soever
    0.59
    Ø©
    0.58
    ãĤ¼
    0.58
    aired
    0.57
    parts
    0.56
    inel
    0.56
    ariat
    0.55
     thereof
    0.55
    Activations Density 0.034%

    No Known Activations