© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17064
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving promotional offers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to frequency, particularly those implying offers, updates, and communications that occur irregularly or occasionally

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    CDC
    -0.82
    Recomm
    -0.82
    rets
    -0.78
    ACTED
    -0.78
    atche
    -0.77
    åĤ
    -0.73
    iants
    -0.73
    lda
    -0.70
    shi
    -0.69
    rollers
    -0.68
    POSITIVE LOGITS
    etheless
    1.06
     bouts
    1.02
     occasional
    0.96
     glimps
    0.95
     commer
    0.87
     occurrences
    0.85
     exceptions
    0.85
     occas
    0.84
     occurrence
    0.84
     periodic
    0.84
    Activations Density 0.007%

    No Known Activations