© 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. 10-RES-JB
    11. 7860
    Prev
    Next
    INDEX
    Explanations

    information related to sports achievements and personal background of athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to awards and achievements in sports or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tame
    -0.76
     invaders
    -0.76
     shoppers
    -0.74
     prud
    -0.73
     garden
    -0.72
     visitors
    -0.70
     invading
    -0.70
     trickle
    -0.69
     clamp
    -0.69
     explan
    -0.69
    POSITIVE LOGITS
     Became
    1.34
     Played
    1.29
     Career
    1.27
    Joined
    1.26
    Favorite
    1.20
    Born
    1.18
     Died
    1.17
     Started
    1.17
    Personal
    1.09
    ometown
    1.09
    Activations Density 0.323%

    No Known Activations