© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6419
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals starting or beginning something

    oai_token-act-pair · gpt-3.5-turbo

    references to player positions, specifically regarding "starters" in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Political
    -0.75
    metic
    -0.67
    Jud
    -0.67
    atial
    -0.66
    images
    -0.64
    aud
    -0.64
     perverse
    -0.63
    ud
    -0.63
     Imag
    -0.61
     Psychological
    -0.61
    POSITIVE LOGITS
     starter
    3.96
     Starter
    2.57
     starters
    2.45
    starter
    2.27
     starting
    1.41
     reliever
    1.40
    starting
    1.36
     beginner
    1.21
     pitcher
    1.04
     burner
    1.01
    Activations Density 0.014%

    No Known Activations