© 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. 3-RES-JB
    11. 20268
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems or challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or colons indicating the start of explanations or lists

    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
    oud
    -0.74
     tremend
    -0.73
    undai
    -0.72
    ouble
    -0.67
    =~=~
    -0.66
    ilion
    -0.66
     misunder
    -0.65
    erver
    -0.65
     subur
    -0.65
    iban
    -0.64
    POSITIVE LOGITS
     namely
    1.01
     Provided
    0.82
     Whereas
    0.78
     Bye
    0.78
    YES
    0.77
     Why
    0.76
     "âĢ¦
    0.71
     They
    0.69
    $$$$
    0.69
     Unless
    0.68
    Activations Density 0.168%

    No Known Activations