© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 18505
    Prev
    Next
    INDEX
    Explanations

    the word "ONE" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "One."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rador
    -0.79
    rawler
    -0.79
    ickr
    -0.78
    ruary
    -0.76
    andum
    -0.76
    lishes
    -0.75
    avorite
    -0.74
    lishing
    -0.72
    achusetts
    -0.72
    lished
    -0.72
    POSITIVE LOGITS
     Hundred
    0.90
    xus
    0.85
    gger
    0.80
    esan
    0.79
     Direction
    0.72
    lihood
    0.70
    hood
    0.70
     hundred
    0.69
     Thousand
    0.69
    horn
    0.66
    Activations Density 0.059%

    No Known Activations