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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 7-RES-JB
    6. 10603
    Prev
    Next
    INDEX
    Explanations

    the word "lend" or its variations in a context of providing support, offering help, or adding weight to something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "lend"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aspx
    -0.65
    alde
    -0.65
    rpm
    -0.63
     WATCHED
    -0.62
    anwhile
    -0.59
    pora
    -0.59
    KING
    -0.59
    ascus
    -0.58
    «
    -0.58
    ARD
    -0.57
    POSITIVE LOGITS
     cred
    0.97
     lend
    0.91
     lent
    0.87
     lending
    0.87
    ament
    0.83
    endum
    0.78
    shire
    0.76
    stocks
    0.74
    rils
    0.74
     generously
    0.73
    Activations Density 0.020%

    No Known Activations