Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7111
    Prev
    Next
    INDEX
    Explanations

    descriptions of a skilled and balanced athlete, particularly highlighting their abilities in a sport

    oai_token-act-pair · gpt-3.5-turbo

    attributes and skills of a player in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Publication
    -0.89
    codes
    -0.79
    IRE
    -0.77
     ®
    -0.74
    utsch
    -0.72
     Publishing
    -0.71
     publishes
    -0.71
     censored
    -0.71
     publisher
    -0.67
     Online
    -0.67
    POSITIVE LOGITS
     underrated
    1.05
     athlet
    1.04
     athleticism
    1.04
     versatility
    1.04
     offensively
    1.02
     defensively
    1.01
     versatile
    0.94
     positional
    0.91
     rookie
    0.88
     rookies
    0.87
    Activations Density 0.964%

    No Known Activations