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. 4-RES-JB
    6. 3410
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complaint" within text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of formal complaints

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

    No Comments

    Negative Logits
    aughs
    -0.80
    itals
    -0.78
    raham
    -0.77
    mers
    -0.75
    eton
    -0.71
    artifacts
    -0.70
    lasses
    -0.69
    ocrates
    -0.68
    bern
    -0.67
    ooks
    -0.67
    POSITIVE LOGITS
     complaints
    1.06
     complaint
    1.00
     alleging
    0.96
     filed
    0.85
     lodged
    0.81
     alleges
    0.78
     against
    0.77
    isance
    0.77
     leveled
    0.76
    naires
    0.75
    Activations Density 0.020%

    No Known Activations