Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1361
    Prev
    Next
    INDEX
    Explanations

    mentions of threats, especially those related to violence or national security

    oai_token-act-pair · gpt-3.5-turbo

    mentions of threats, particularly those related to violence and national security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mys
    -0.82
    ilts
    -0.79
    arist
    -0.76
    orph
    -0.70
    porter
    -0.68
    Band
    -0.67
    otide
    -0.66
    baum
    -0.66
    NAS
    -0.66
    puted
    -0.65
    POSITIVE LOGITS
     threats
    1.32
     threat
    1.06
     undermin
    0.96
    threat
    0.93
     challeng
    0.92
     Threat
    0.89
     threaten
    0.88
     proble
    0.88
     threatening
    0.83
     menacing
    0.83
    Activations Density 0.009%

    No Known Activations