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. 2-RES-JB
    6. 24301
    Prev
    Next
    INDEX
    Explanations

    expressions of preference

    oai_token-act-pair · gpt-3.5-turbo

    expressions of preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eval
    -0.74
    idem
    -0.73
    Article
    -0.73
    ammy
    -0.73
    pack
    -0.71
    Chapter
    -0.70
    Americ
    -0.70
    Impl
    -0.69
    angers
    -0.68
    chapter
    -0.67
    POSITIVE LOGITS
    yip
    0.80
    ably
    0.79
    lihood
    0.76
     preferring
    0.75
    swer
    0.72
     prefers
    0.70
     favoured
    0.70
    ancy
    0.69
     pse
    0.69
    itism
    0.68
    Activations Density 0.009%

    No Known Activations