© 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. 0-RES-JB
    11. 7631
    Prev
    Next
    INDEX
    Explanations

    mentions of injuries or physical conditions related to the leg

    oai_token-act-pair · gpt-3.5-turbo

    references to 'leg' and related injuries or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freeze
    -0.73
     Clouds
    -0.71
     Comet
    -0.69
    pool
    -0.68
     Sorcerer
    -0.67
    ulators
    -0.67
    olve
    -0.66
    define
    -0.66
    illery
    -0.64
     Zy
    -0.64
    POSITIVE LOGITS
     leg
    3.79
     Leg
    2.12
     legs
    2.04
     thigh
    1.64
    leg
    1.53
     foot
    1.46
     arm
    1.44
     limb
    1.42
     knee
    1.41
    Leg
    1.41
    Activations Density 0.008%

    No Known Activations