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. 6-RES-JB
    6. 4902
    Prev
    Next
    INDEX
    Explanations

    statistics or reports on incidents involving people being injured, wounded, arrested, killed, or evacuated

    oai_token-act-pair · gpt-3.5-turbo

    mentions of injuries or casualties involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.80
    issance
    -0.76
     Advertisement
    -0.70
     Unless
    -0.66
    feeding
    -0.65
    essor
    -0.64
     Ples
    -0.64
     Dating
    -0.63
     mund
    -0.62
     Forget
    -0.62
    POSITIVE LOGITS
    athi
    0.89
     flown
    0.82
     reportedly
    0.79
     already
    0.77
     hospitalized
    0.76
     injured
    0.76
     crammed
    0.75
     apiece
    0.74
     killed
    0.73
     enrolled
    0.71
    Activations Density 0.205%

    No Known Activations