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. 12-RES-JB
    6. 15088
    Prev
    Next
    INDEX
    Explanations

    descriptions of incidents or events involving law enforcement or criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to crime, legal matters, and law enforcement situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     [â̦]
    -0.68
     âμ
    -0.66
     ÂŃ
    -0.65
     pudding
    -0.59
     âĢ
    -0.59
     jaws
    -0.59
     resusc
    -0.58
    ↵
    -0.58
     ener
    -0.57
     discern
    -0.57
    POSITIVE LOGITS
    Special
    1.23
    Any
    1.19
    Alternative
    1.18
    To
    1.18
    For
    1.17
    No
    1.17
    Right
    1.16
    Only
    1.16
    Information
    1.16
    Edited
    1.16
    Activations Density 0.569%

    No Known Activations