© 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. 2-RES-JB
    11. 24010
    Prev
    Next
    INDEX
    Explanations

    references to violent acts involving firearms or accusations of wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    references to formal incident reports and violent acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefferson
    -0.71
    qqa
    -0.71
    oline
    -0.68
     Shutterstock
    -0.67
     intern
    -0.65
     Candy
    -0.64
     interns
    -0.63
     retina
    -0.62
     sock
    -0.61
     Intern
    -0.61
    POSITIVE LOGITS
     FIR
    0.94
    sa
    0.92
     corrid
    0.88
    sheet
    0.80
    eous
    0.78
    eways
    0.78
    busters
    0.77
    ship
    0.76
    ebin
    0.76
    ging
    0.76
    Activations Density 0.026%

    No Known Activations