© 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. 3-RES-JB
    11. 14790
    Prev
    Next
    INDEX
    Explanations

    references to the human body part 'shoulder'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "shoulder."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovych
    -0.84
    eer
    -0.75
    icative
    -0.73
    esis
    -0.73
     Vide
    -0.72
    ularity
    -0.72
    ettings
    -0.71
    election
    -0.69
    antis
    -0.69
    esters
    -0.69
    POSITIVE LOGITS
     shoulder
    1.29
     blades
    1.14
    bone
    0.93
     shoulders
    0.92
     straps
    0.88
     blade
    0.87
     shrug
    0.86
     joints
    0.86
     pads
    0.85
     lobe
    0.85
    Activations Density 0.011%

    No Known Activations