© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10748
    Prev
    Next
    INDEX
    Explanations

    references to PC gaming

    oai_token-act-pair · gpt-3.5-turbo

    mentions of personal computers, specifically related to their market performance and specifications

    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
    glers
    -0.89
    enance
    -0.77
    quez
    -0.75
    htar
    -0.73
    sweet
    -0.71
    changed
    -0.68
     Mayweather
    -0.67
     Ney
    -0.66
    ymes
    -0.66
    chell
    -0.66
    POSITIVE LOGITS
     Gamer
    1.26
    Gaming
    1.10
    ORPG
    1.05
    PDATE
    1.05
    Games
    1.03
     gaming
    0.96
    GS
    0.95
    SO
    0.94
     gamer
    0.92
    oreal
    0.91
    Activations Density 0.025%

    No Known Activations