© 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
    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. 1837
    Prev
    Next
    INDEX
    Explanations

    keywords related to instructions or processes, such as cooking or building

    oai_token-act-pair · gpt-3.5-turbo

    references to food and cooking techniques

    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
    partisan
    -0.83
    atform
    -0.60
     Voting
    -0.60
     Patreon
    -0.59
    netflix
    -0.59
     Fiscal
    -0.58
    PAC
    -0.57
    intend
    -0.56
    hearted
    -0.56
     Founders
    -0.56
    POSITIVE LOGITS
     guiActiveUn
    0.74
    ãĤ©
    0.64
    emonium
    0.62
    VERTISEMENT
    0.60
     mode
    0.57
     traverse
    0.55
    zers
    0.55
     prest
    0.53
     eject
    0.52
     susp
    0.51
    Activations Density 2.054%

    No Known Activations