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

    Neuronpedia

    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. 2-RES-JB
    11. 17366
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities that are leading in their respective fields

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "leading."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ager
    -0.71
    ombies
    -0.68
    agen
    -0.68
    nery
    -0.66
    cube
    -0.66
    ugi
    -0.65
    ategor
    -0.65
    ope
    -0.63
    apy
    -0.63
    orrow
    -0.62
    POSITIVE LOGITS
     Leading
    0.99
     leading
    0.89
    boards
    0.84
    wcs
    0.83
    lines
    0.76
    lead
    0.75
    Lead
    0.75
    better
    0.75
     scorer
    0.74
    leading
    0.71
    Activations Density 0.016%

    No Known Activations