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. 10344
    Prev
    Next
    INDEX
    Explanations

    positive commentary and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal preference and emotional responses

    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
     legisl
    -0.57
     constitutional
    -0.57
     unlawfully
    -0.56
    economic
    -0.56
     elector
    -0.56
     administr
    -0.54
     wage
    -0.54
     ministerial
    -0.54
     constitutionally
    -0.53
     jointly
    -0.53
    POSITIVE LOGITS
     Horror
    0.58
     Weird
    0.55
     Rebirth
    0.55
    Laughs
    0.55
     Animation
    0.55
     Hitch
    0.54
     Wonderland
    0.54
     Ragnarok
    0.53
    laughs
    0.53
     Lovecraft
    0.53
    Activations Density 4.488%

    No Known Activations