Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9379
    Prev
    Next
    INDEX
    Explanations

    superlatives and extremes, such as "most" or "greatest"

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives indicating extreme qualities or ranks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.73
    styles
    -0.66
    skirts
    -0.65
    rahim
    -0.64
    ancies
    -0.64
     Regist
    -0.64
    åī
    -0.63
    Magic
    -0.63
    events
    -0.63
    ategor
    -0.63
    POSITIVE LOGITS
     conceivable
    0.95
    hest
    0.87
     possible
    0.85
    est
    0.82
     thing
    0.81
    liest
    0.80
     conduit
    0.77
     beneficiary
    0.77
     indicator
    0.77
     clue
    0.77
    Activations Density 0.121%

    No Known Activations