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. 9-RES-JB
    6. 841
    Prev
    Next
    INDEX
    Explanations

    items related to theft

    oai_token-act-pair · gpt-3.5-turbo

    references to consumer products and merchandise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourced
    -0.81
     Accountability
    -0.80
    plementation
    -0.79
    imester
    -0.78
     qualifier
    -0.73
    heast
    -0.72
    agonist
    -0.72
    aclysm
    -0.70
    ocracy
    -0.70
    STATE
    -0.70
    POSITIVE LOGITS
     toys
    1.33
     iPads
    1.25
     clothing
    1.23
     DVDs
    1.23
     furniture
    1.23
     jewelry
    1.22
     tablets
    1.20
     towels
    1.18
     magazines
    1.17
     cigarettes
    1.16
    Activations Density 0.290%

    No Known Activations