© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14147
    Prev
    Next
    INDEX
    Explanations

    punctuation and ellipses

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or ellipses-like sequences 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ«
    -0.93
    otine
    -0.78
     mobilized
    -0.75
    emia
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.73
    ãĥ³ãĤ¸
    -0.71
     empath
    -0.69
    ocratic
    -0.68
    nikov
    -0.68
     ostr
    -0.66
    POSITIVE LOGITS
    .....
    1.00
    ....
    1.00
    ...]
    0.92
    mmmm
    0.90
    BUT
    0.89
     ....
    0.87
    ↵Âł
    0.86
    php
    0.84
     Whats
    0.82
    .........
    0.82
    Activations Density 0.005%

    No Known Activations