© 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. 10-RES-JB
    11. 2697
    Prev
    Next
    INDEX
    Explanations

    actions related to conflict and physical altercations

    oai_token-act-pair · gpt-3.5-turbo

    key events related to criminal activity and violence

    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
    utical
    -0.84
    actionDate
    -0.83
    soDeliveryDate
    -0.79
    isSpecialOrderable
    -0.78
    imester
    -0.71
     Ranking
    -0.70
     Optim
    -0.70
     blogging
    -0.64
     Tues
    -0.64
    college
    -0.64
    POSITIVE LOGITS
     grabbed
    1.32
     yelled
    1.32
     threw
    1.27
     proceeded
    1.21
     shoved
    1.19
     jumped
    1.18
     exited
    1.16
     shouted
    1.16
     noticed
    1.15
     slammed
    1.15
    Activations Density 0.272%

    No Known Activations