© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18820
    Prev
    Next
    INDEX
    Explanations

    proper names and titles starting with the letter 'J'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'J'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     galleries
    -0.70
     pony
    -0.68
     captcha
    -0.67
     peanuts
    -0.65
     clipboard
    -0.65
     beware
    -0.65
     refreshed
    -0.64
     MacArthur
    -0.64
     Gret
    -0.61
     \(\
    -0.61
    POSITIVE LOGITS
    upiter
    1.44
    unction
    1.37
    ournals
    1.36
    oint
    1.35
    ourney
    1.32
    ungle
    1.31
    ealous
    1.30
    asper
    1.30
    umping
    1.25
    avascript
    1.25
    Activations Density 0.028%

    No Known Activations