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. 10115
    Prev
    Next
    INDEX
    Explanations

    names or phrases containing the word "Reese" followed by different numbers

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to people and places

    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
    intosh
    -0.67
     Dragonbound
    -0.67
     Cumber
    -0.64
    netic
    -0.63
    busters
    -0.60
     heroism
    -0.59
     Alcohol
    -0.59
    natural
    -0.59
    raviolet
    -0.58
     deduction
    -0.58
    POSITIVE LOGITS
    ppe
    1.15
    zzo
    1.04
    gypt
    1.01
    zza
    0.96
    phant
    0.91
    ichen
    0.90
    uth
    0.89
    cker
    0.88
    este
    0.88
    achable
    0.87
    Activations Density 0.018%

    No Known Activations