© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15529
    Prev
    Next
    INDEX
    Explanations

    the word "Let's"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "s" in various contexts

    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
     respiratory
    -0.66
     malaria
    -0.62
     carcin
    -0.61
     hemor
    -0.61
     consolid
    -0.61
     stewards
    -0.60
     refere
    -0.59
     pree
    -0.58
     Reef
    -0.58
     annex
    -0.58
    POSITIVE LOGITS
    kaya
    0.93
    omew
    0.93
    atisf
    0.90
    ometime
    0.90
    iblings
    0.90
    lightly
    0.90
    terday
    0.89
    wered
    0.84
    olution
    0.83
    linger
    0.82
    Activations Density 0.225%

    No Known Activations