© 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. 11-RES-JB
    11. 12963
    Prev
    Next
    INDEX
    Explanations

    names starting with "Oh" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    the name "John" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JUSTICE
    -0.66
     seams
    -0.63
    erity
    -0.61
    Fal
    -0.59
     Pixie
    -0.58
     Reborn
    -0.56
     Fired
    -0.56
    Closure
    -0.53
    Psy
    -0.53
     Legions
    -0.52
    POSITIVE LOGITS
    ansen
    1.19
    awks
    1.14
    tml
    1.11
    awk
    1.09
    ttp
    1.09
    ospital
    1.08
    ansson
    1.04
    lers
    1.03
    rab
    1.02
    azard
    1.02
    Activations Density 0.047%

    No Known Activations