© 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. 9-RES-JB
    6. 15777
    Prev
    Next
    INDEX
    Explanations

    words related to approval, positive evaluation, or affirmation

    oai_token-act-pair · gpt-3.5-turbo

    key verbs and expressions that indicate actions or significant concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eni
    -0.69
    pes
    -0.68
    ciating
    -0.64
    ESE
    -0.62
    geon
    -0.62
    ++++++++++++++++
    -0.60
    pedia
    -0.60
    elight
    -0.59
    hene
    -0.58
     Annotations
    -0.58
    POSITIVE LOGITS
    that
    1.33
     that
    1.28
     That
    1.11
     THAT
    1.09
    That
    1.09
     thats
    0.91
    aler
    0.65
    ãĤ¤ãĥĪ
    0.62
    æĺ¯
    0.61
     those
    0.58
    Activations Density 0.187%

    No Known Activations