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. 1-RES-JB
    6. 9800
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to agreements or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "terms" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.76
    ################
    -0.76
    ****************
    -0.76
    ©¶æ¥µ
    -0.73
    rote
    -0.69
    HAEL
    -0.68
    Es
    -0.66
    hs
    -0.65
    ORGE
    -0.64
    ERO
    -0.63
    POSITIVE LOGITS
     terms
    1.17
    terms
    0.96
     Terms
    0.93
    pring
    0.91
    ually
    0.85
    cale
    0.81
    mith
    0.81
    term
    0.76
    ames
    0.70
    manship
    0.69
    Activations Density 0.016%

    No Known Activations