© 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 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. 8-RES-JB
    11. 19311
    Prev
    Next
    INDEX
    Explanations

    acronyms or proper nouns ending with 'O'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'O', particularly in various contexts and combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awed
    -0.69
    theless
    -0.63
    ifications
    -0.62
     substitutes
    -0.61
    inois
    -0.61
    ulia
    -0.61
    rar
    -0.59
    rity
    -0.58
    ificate
    -0.58
    flies
    -0.57
    POSITIVE LOGITS
    JO
    1.21
    VE
    1.19
    zzi
    1.18
    OPS
    1.13
    LL
    1.13
    XY
    1.12
    lymp
    1.10
    LET
    1.09
    ISE
    1.09
    FILE
    1.08
    Activations Density 0.068%

    No Known Activations