© 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. 3-RES-JB
    11. 23193
    Prev
    Next
    INDEX
    Explanations

    redirects or redirection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "redirect" and its variations

    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
    gerald
    -0.69
    FT
    -0.68
    ellen
    -0.67
    ---------------
    -0.67
    MET
    -0.66
     Gael
    -0.64
     MIA
    -0.63
    acht
    -0.63
    Dutch
    -0.63
     Verge
    -0.63
    POSITIVE LOGITS
     redirect
    1.31
    irection
    1.06
     redirected
    1.02
    irect
    0.95
     destro
    0.84
    oute
    0.84
     directing
    0.82
     srf
    0.79
     deflect
    0.78
     rewriting
    0.78
    Activations Density 0.013%

    No Known Activations