© 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. 0-RES-JB
    11. 15435
    Prev
    Next
    INDEX
    Explanations

    adverbs related to certainty

    oai_token-act-pair · gpt-3.5-turbo

    affirmative or emphatic statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emergency
    -0.57
    enta
    -0.52
     Base
    -0.52
     Use
    -0.52
     Items
    -0.51
    units
    -0.51
     Users
    -0.51
     "+
    -0.50
     BAL
    -0.49
     Takeru
    -0.49
    POSITIVE LOGITS
     certainly
    3.41
     definitely
    2.54
     surely
    2.32
     undoubtedly
    2.20
     doubtless
    2.14
     Certainly
    1.82
    Certainly
    1.78
     probably
    1.76
     obviously
    1.72
     indeed
    1.66
    Activations Density 0.015%

    No Known Activations