© 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. 18956
    Prev
    Next
    INDEX
    Explanations

    mentions of actions involving sidestepping

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sid" or its variations in different 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
    女
    -0.74
    ASED
    -0.62
     retard
    -0.62
    Ļ½
    -0.61
    姫
    -0.60
     Abyss
    -0.60
     UNESCO
    -0.59
     grandparents
    -0.59
     doomed
    -0.58
     magnets
    -0.57
    POSITIVE LOGITS
    eways
    1.38
    este
    1.38
    etr
    1.35
    emark
    1.11
    eworks
    1.05
    eline
    1.05
    eto
    1.04
    uction
    1.04
    uctive
    1.03
    emen
    1.02
    Activations Density 0.036%

    No Known Activations