© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    the word "ones" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to items or things described as "ones."

    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
    Cl
    -0.69
    Phys
    -0.68
     Directors
    -0.63
    754
    -0.62
    Leader
    -0.62
    Attorney
    -0.62
    Lead
    -0.62
     Pwr
    -0.62
    Dem
    -0.61
    ITED
    -0.61
    POSITIVE LOGITS
    hots
    0.89
    omething
    0.83
    ones
    0.72
    etter
    0.72
    yton
    0.71
     emoji
    0.70
    ngth
    0.70
    auga
    0.69
    pointers
    0.68
     immutable
    0.68
    Activations Density 0.018%

    No Known Activations