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. 0-RES-JB
    6. 23639
    Prev
    Next
    INDEX
    Explanations

    names of a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely associated with discussion or controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crown
    -0.68
     capsule
    -0.68
     av
    -0.66
     region
    -0.65
     bol
    -0.64
     ranks
    -0.64
     pant
    -0.64
     metal
    -0.63
     Gob
    -0.62
     burns
    -0.62
    POSITIVE LOGITS
    Reilly
    4.53
     Reilly
    1.91
    Leary
    1.51
    Brien
    1.42
    Keefe
    1.38
    Neill
    1.35
    Connell
    1.32
    Connor
    1.23
    Sullivan
    1.20
    Donnell
    1.19
    Activations Density 0.008%

    No Known Activations