© 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. 4-RES-JB
    11. 22600
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods indicating the end of sentences

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

    No Comments

    Negative Logits
     optimizations
    -0.76
     satell
    -0.67
     advoc
    -0.66
     juicy
    -0.64
     exha
    -0.62
     splash
    -0.61
     servicing
    -0.61
     fruitful
    -0.60
     informed
    -0.60
    interstitial
    -0.60
    POSITIVE LOGITS
    Ö¼
    0.82
    soDeliveryDate
    0.80
    Downloadha
    0.78
    [/
    0.77
    assetsadobe
    0.76
    tumblr
    0.75
    =""
    0.74
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.72
    aspx
    0.70
    SPONSORED
    0.70
    Activations Density 0.378%

    No Known Activations