© 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. 1896
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or assurance

    oai_token-act-pair · gpt-3.5-turbo

    affirmative phrases or confirmations

    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
    âĵĺ
    -0.75
    RAW
    -0.68
    LESS
    -0.67
    utenberg
    -0.67
    inational
    -0.67
     UCHIJ
    -0.65
    inventoryQuantity
    -0.64
    natureconservancy
    -0.64
    mercial
    -0.63
    âĸº
    -0.60
    POSITIVE LOGITS
    terday
    0.77
    ndra
    0.73
    hea
    0.72
     Virtue
    0.71
    ties
    0.70
    xus
    0.70
    ardon
    0.70
    sure
    0.69
    antha
    0.68
     enough
    0.67
    Activations Density 0.024%

    No Known Activations