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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9253
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that end with periods and seem to be part of a list or series

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -1.03
     carbohyd
    -1.02
     earthqu
    -1.00
     pione
    -0.94
     volunte
    -0.94
     gobl
    -0.90
    Þ
    -0.88
     tremend
    -0.86
    senal
    -0.86
     advoc
    -0.84
    POSITIVE LOGITS
     Conversely
    1.69
     Likewise
    1.61
     Similarly
    1.57
     Moreover
    1.51
     Worse
    1.47
     Nonetheless
    1.42
     Furthermore
    1.37
     Hence
    1.36
    Similarly
    1.35
    Likewise
    1.35
    Activations Density 0.458%

    No Known Activations