© 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. 11-RES-JB
    11. 22298
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements or necessities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to financial decisions and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misunder
    -0.69
     )]
    -0.63
     playful
    -0.54
     sugg
    -0.53
     whim
    -0.52
     insin
    -0.51
     blame
    -0.51
     suggestion
    -0.51
     appre
    -0.51
     speculation
    -0.50
    POSITIVE LOGITS
     lest
    1.21
     before
    1.17
     BEFORE
    1.06
    before
    1.01
     beforehand
    0.99
     Otherwise
    0.98
     ASAP
    0.97
     manually
    0.96
     urgently
    0.88
     separately
    0.87
    Activations Density 0.762%

    No Known Activations