© 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. 4-RES-JB
    11. 12214
    Prev
    Next
    INDEX
    Explanations

    redirects or mentions of redirecting actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "redirect" and its variations, indicating references to changing or altering direction or focus

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

    No Comments

    Negative Logits
    MET
    -0.73
    acht
    -0.70
    gerald
    -0.68
    makers
    -0.65
    ellen
    -0.64
    ---------------
    -0.64
    FT
    -0.64
    Commission
    -0.63
    board
    -0.63
    Ö¼
    -0.61
    POSITIVE LOGITS
     redirect
    1.19
     redirected
    0.96
    irection
    0.93
    oute
    0.84
    irect
    0.82
     srf
    0.79
    resses
    0.77
    htaking
    0.76
     deflect
    0.74
    ressing
    0.74
    Activations Density 0.014%

    No Known Activations