© 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. 11643
    Prev
    Next
    INDEX
    Explanations

    keywords and variable names related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming and computer science concepts

    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
    pee
    -0.70
    eport
    -0.69
    andal
    -0.69
    qua
    -0.68
    issance
    -0.68
    hur
    -0.66
    ensical
    -0.65
    eful
    -0.65
    pees
    -0.63
    uce
    -0.63
    POSITIVE LOGITS
     names
    1.45
    Name
    1.43
     IDs
    1.39
     name
    1.36
    Names
    1.26
     identifiers
    1.25
    names
    1.24
    NAME
    1.22
    name
    1.20
     identifier
    1.18
    Activations Density 0.292%

    No Known Activations