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. 11-RES-JB
    6. 10805
    Prev
    Next
    INDEX
    Explanations

    information related to news events, such as suspects, victims, and incidents, along with comments and statements made in response to these events

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to suspects and ongoing investigations

    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
     darn
    -0.68
     HUGE
    -0.67
     ain
    -0.66
     EVERY
    -0.64
     irresist
    -0.63
    ummy
    -0.62
     damn
    -0.62
     beware
    -0.61
     NEVER
    -0.60
     beautifully
    -0.60
    POSITIVE LOGITS
     nor
    1.58
    nor
    1.26
     or
    1.05
     anymore
    0.99
    yet
    0.93
     except
    0.85
     yet
    0.85
     specifics
    0.81
     but
    0.80
     either
    0.77
    Activations Density 0.559%

    No Known Activations