© 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. 6-RES-JB
    11. 17321
    Prev
    Next
    INDEX
    Explanations

    descriptions of performance characteristics and physical abilities, particularly in sports

    oai_token-act-pair · gpt-3.5-turbo

    attributes and assessments related to player performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archives
    -0.77
     Publication
    -0.76
     censored
    -0.75
     commem
    -0.75
    utsch
    -0.70
    IRE
    -0.70
     Editorial
    -0.68
     organisers
    -0.65
     crem
    -0.65
     embargo
    -0.64
    POSITIVE LOGITS
     versatility
    1.06
     versatile
    0.98
     athleticism
    0.98
     athlet
    0.94
     underrated
    0.93
     defensively
    0.92
    Weak
    0.88
     situational
    0.85
     offensively
    0.85
     rookie
    0.85
    Activations Density 0.681%

    No Known Activations