© 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 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. 2-RES-JB
    11. 19710
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or sequence

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rollers
    -0.74
     cellul
    -0.73
    aucas
    -0.71
    agonist
    -0.71
    nut
    -0.70
     toast
    -0.69
    rection
    -0.66
    agram
    -0.64
    unker
    -0.62
    agon
    -0.62
    POSITIVE LOGITS
    HK
    0.69
    emouth
    0.67
    QUI
    0.66
    TPPStreamerBot
    0.62
    ADRA
    0.62
    debian
    0.62
    index
    0.61
    åĬ
    0.61
    Prosecut
    0.60
    Cont
    0.59
    Activations Density 0.000%

    No Known Activations