© 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. 4-RES-JB
    6. 7811
    Prev
    Next
    INDEX
    Explanations

    the ellipsis punctuation mark ('...')

    oai_token-act-pair · gpt-3.5-turbo

    ellipses and punctuation marks, possibly indicating pauses or omissions in text

    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
    mith
    -0.78
     charms
    -0.70
    grass
    -0.69
    achus
    -0.67
    chnology
    -0.66
    ldon
    -0.63
    TPPStreamerBot
    -0.61
     purse
    -0.60
     labs
    -0.60
     exch
    -0.59
    POSITIVE LOGITS
    ago
    0.67
    fle
    0.66
    BRE
    0.66
    imon
    0.66
    "]=>
    0.66
    actionDate
    0.65
    ILLE
    0.65
    wait
    0.64
    mosp
    0.64
    pedia
    0.63
    Activations Density 0.026%

    No Known Activations