© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18761
    Prev
    Next
    INDEX
    Explanations

    notable achievements and historical events related to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to milestones or first occurrences in various contexts

    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
     surrounds
    -0.62
    xual
    -0.57
    oros
    -0.57
    issues
    -0.57
    pots
    -0.57
     [];
    -0.57
     nightmares
    -0.56
     haun
    -0.56
     pockets
    -0.56
     equation
    -0.56
    POSITIVE LOGITS
     first
    1.40
    first
    1.39
    Third
    1.38
     sixth
    1.36
     fifth
    1.36
     seventh
    1.34
     fourth
    1.34
    third
    1.33
    fifth
    1.32
    Fourth
    1.31
    Activations Density 0.313%

    No Known Activations