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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23547
    Prev
    Next
    INDEX
    Explanations

    news articles reporting various incidents or events involving crime or accidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" indicating actions or states involving subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Extend
    -0.80
    Reloaded
    -0.73
     avoidance
    -0.66
    velt
    -0.66
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
     newsletters
    -0.66
    umes
    -0.64
    Mods
    -0.64
    Relations
    -0.64
     Countries
    -0.63
    POSITIVE LOGITS
     gunned
    1.39
     stabbed
    1.38
     sentenced
    1.36
     arrested
    1.32
     fatally
    1.29
     abducted
    1.28
     murdered
    1.28
     killed
    1.27
     kidnapped
    1.22
     assaulted
    1.20
    Activations Density 0.155%

    No Known Activations