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. 11-RES-JB
    6. 3286
    Prev
    Next
    INDEX
    Explanations

    topical trends and events likely from online platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trending topics and social discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onyms
    -0.70
    otos
    -0.67
    votes
    -0.67
    Frames
    -0.65
    luent
    -0.64
    Specific
    -0.63
    ãĥĥ
    -0.60
    times
    -0.59
     tranquil
    -0.59
    NOR
    -0.58
    POSITIVE LOGITS
    heet
    1.69
    mith
    1.46
    hip
    1.46
    ystem
    1.41
    creen
    1.40
    cale
    1.37
    erver
    1.36
    pace
    1.34
    cape
    1.31
    hift
    1.27
    Activations Density 0.518%

    No Known Activations