© 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. 4-RES-JB
    11. 6010
    Prev
    Next
    INDEX
    Explanations

    numbers related to durations or bonuses in a gaming context

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to time, distance, and damage in gameplay mechanics

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

    No Comments

    Negative Logits
    llor
    -0.76
    glas
    -0.73
    folk
    -0.68
    acus
    -0.68
     Elias
    -0.67
    actionDate
    -0.66
    icism
    -0.62
     pse
    -0.62
     Samar
    -0.61
     Bashar
    -0.61
    POSITIVE LOGITS
    %-
    0.99
    ½
    0.97
     degrees
    0.96
    %
    0.94
    °
    0.92
     seconds
    0.90
     litres
    0.89
    º
    0.89
     watts
    0.88
    0000
    0.88
    Activations Density 0.338%

    No Known Activations