© 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 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. 3-RES-JB
    11. 24210
    Prev
    Next
    INDEX
    Explanations

    instances where something happens unexpectedly or by mistake

    oai_token-act-pair · gpt-3.5-turbo

    instances of accidental actions or unintended consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teen
    -0.68
    crime
    -0.67
    leaders
    -0.67
    antics
    -0.66
    shall
    -0.65
     Techniques
    -0.65
    thood
    -0.64
    aily
    -0.64
    markets
    -0.62
    resources
    -0.62
    POSITIVE LOGITS
     accidentally
    1.00
     inadvertently
    0.87
     unintentionally
    0.87
    idental
    0.80
     stumbled
    0.79
    identally
    0.76
     bumped
    0.75
    ãĤ©
    0.75
     drown
    0.73
     combust
    0.73
    Activations Density 0.010%

    No Known Activations