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. 3-RES-JB
    6. 10928
    Prev
    Next
    INDEX
    Explanations

    references to sexual activity or related issues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sexual activity and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.63
    CS
    -0.63
    late
    -0.62
    Sus
    -0.61
    Ill
    -0.61
    bee
    -0.60
    Labor
    -0.60
    Strike
    -0.59
    early
    -0.59
     Surve
    -0.58
    POSITIVE LOGITS
    kees
    0.84
    been
    0.82
    urred
    0.71
    ointed
    0.71
    kered
    0.70
     knack
    0.68
    olas
    0.65
    esthesia
    0.63
     firsthand
    0.63
     qual
    0.63
    Activations Density 0.536%

    No Known Activations