© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12525
    Prev
    Next
    INDEX
    Explanations

    instances of physical harm or violence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "shot in" followed by body parts, indicating violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urable
    -0.67
    DH
    -0.66
    Wire
    -0.65
    era
    -0.58
    ENT
    -0.57
    enta
    -0.56
    Maps
    -0.55
    Talk
    -0.55
    Quantity
    -0.55
    istries
    -0.54
    POSITIVE LOGITS
     abdomen
    0.94
     cheek
    0.93
     thigh
    0.91
     stride
    0.89
     buttocks
    0.87
     groin
    0.84
     torso
    0.82
    astern
    0.82
     forehead
    0.81
     situ
    0.80
    Activations Density 0.071%

    No Known Activations