© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6380
    Prev
    Next
    INDEX
    Explanations

    titles of various forms of media such as books, music albums, and movies

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases mentioning various types of art or literature

    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
    soType
    -0.92
    Token
    -0.88
    groups
    -0.85
    âĹ¼
    -0.82
     Cosponsors
    -0.81
    BILITIES
    -0.80
     Preferred
    -0.80
    btn
    -0.80
    Materials
    -0.77
    attr
    -0.77
    POSITIVE LOGITS
     thriller
    1.46
     memoir
    1.36
     satire
    1.36
     tale
    1.28
     autobi
    1.26
     masterpiece
    1.25
     anthology
    1.24
     sequel
    1.22
     documentary
    1.21
     autobiography
    1.20
    Activations Density 0.336%

    No Known Activations