© 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. 7-RES-JB
    11. 1587
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, within the text

    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
    intendent
    -0.83
    reet
    -0.80
    elve
    -0.74
     cherished
    -0.72
     credential
    -0.72
    Å«
    -0.72
     enroll
    -0.72
     elevated
    -0.72
     enrolled
    -0.72
     unaff
    -0.70
    POSITIVE LOGITS
     Anyway
    1.54
     Also
    1.30
     Basically
    1.28
     Otherwise
    1.26
    Anyway
    1.26
     :)
    1.23
     Secondly
    1.22
     ;)
    1.21
     Alternatively
    1.19
    edit
    1.19
    Activations Density 0.544%

    No Known Activations