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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21223
    Prev
    Next
    INDEX
    Explanations

    numerical quantities related to incidents of violence

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numbers of victims or casualties in violent incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.80
    biology
    -0.71
     evolve
    -0.67
    agame
    -0.67
    arist
    -0.66
    Platform
    -0.66
    Theme
    -0.66
     immortality
    -0.65
    ktop
    -0.65
     hegemony
    -0.65
    POSITIVE LOGITS
    teen
    0.97
     suspected
    0.93
     eyewitness
    0.90
     unidentified
    0.89
     suspects
    0.87
     gunshots
    0.83
    een
    0.82
     gunshot
    0.80
     policemen
    0.80
     consecutive
    0.79
    Activations Density 0.240%

    No Known Activations