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. 7-RES-JB
    6. 16331
    Prev
    Next
    INDEX
    Explanations

    mentions of email newsletters and promotions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating lists or enumerations

    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
    aimon
    -0.65
     antit
    -0.61
    panic
    -0.61
    eton
    -0.60
    atures
    -0.59
    legates
    -0.58
     tert
    -0.58
    robe
    -0.58
    keyes
    -0.58
     âĢķ
    -0.58
    POSITIVE LOGITS
     please
    0.86
     eh
    0.74
    please
    0.71
    oulos
    0.68
     huh
    0.68
     PLEASE
    0.67
    yip
    0.64
     INCLUD
    0.63
     featuring
    0.62
     courtesy
    0.62
    Activations Density 0.168%

    No Known Activations