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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 4638
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication such as quotes and statements

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific unusual character sequence within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dispers
    -0.74
     casting
    -0.69
     drawing
    -0.67
     scattering
    -0.66
     scatter
    -0.66
     relocation
    -0.65
     conservation
    -0.65
     detached
    -0.64
     confinement
    -0.64
     grazing
    -0.63
    POSITIVE LOGITS
    ¹
    1.11
    Į
    1.03
    į
    1.01
    £
    1.00
    ¡
    1.00
    Ĭ
    0.95
    ¤
    0.94
    ı
    0.91
    okia
    0.90
    Ī
    0.89
    Activations Density 0.259%

    No Known Activations