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. 7288
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation marks like periods and exclamation points

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, particularly periods in various contexts

    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
    ',"
    -0.66
    XM
    -0.65
    WP
    -0.65
    URL
    -0.64
    Mobil
    -0.63
    RGB
    -0.62
    å§
    -0.60
    API
    -0.59
    ZX
    -0.59
    RL
    -0.59
    POSITIVE LOGITS
    ↵Âł
    1.02
     Âł
    0.93
     Âł Âł
    0.92
     ³³
    0.89
    ³³
    0.87
     Secondly
    0.87
     Hence
    0.86
     However
    0.84
     princ
    0.84
     Its
    0.83
    Activations Density 0.503%

    No Known Activations