© 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. 16154
    Prev
    Next
    INDEX
    Explanations

    pairs of contrasting roles or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to legal or criminal matters

    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
    stones
    -0.97
    ets
    -0.78
     Bows
    -0.77
    nia
    -0.74
    uations
    -0.73
    ETS
    -0.71
    years
    -0.71
    \.
    -0.71
    marks
    -0.71
    ums
    -0.71
    POSITIVE LOGITS
     careg
    1.47
     beneficiary
    1.46
     performer
    1.46
     attacker
    1.44
     receiver
    1.44
     recipient
    1.42
     participant
    1.42
     perpetrator
    1.42
     buyer
    1.41
     abuser
    1.40
    Activations Density 0.364%

    No Known Activations