© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1001
    Prev
    Next
    INDEX
    Explanations

    countable objects or quantities that are large in number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "thousand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imir
    -0.83
    foundation
    -0.79
    raising
    -0.67
    raints
    -0.67
    liga
    -0.66
    obal
    -0.66
    bid
    -0.64
    icipated
    -0.64
    density
    -0.64
    abilities
    -0.63
    POSITIVE LOGITS
     Thousand
    1.07
     thousand
    1.05
     000
    0.99
     ILCS
    0.94
     dollars
    0.89
     miles
    0.88
    aires
    0.86
     kilometers
    0.86
    naire
    0.86
     pounds
    0.85
    Activations Density 0.006%

    No Known Activations