© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 24400
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks, especially commas and special characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas and conjunctions

    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
    assian
    -0.59
    href
    -0.49
    owan
    -0.47
    rison
    -0.46
    200000
    -0.46
    HAM
    -0.46
    Enlarge
    -0.45
    reporting
    -0.44
    oji
    -0.42
    ief
    -0.41
    POSITIVE LOGITS
     the
    1.37
    the
    1.28
     THE
    0.96
    The
    0.91
     The
    0.84
     tha
    0.78
    THE
    0.76
    thel
    0.69
    ethe
    0.68
     those
    0.54
    Activations Density 1.362%

    No Known Activations