© 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. 11-RES-JB
    6. 129
    Prev
    Next
    INDEX
    Explanations

    "do'' or ''did'' statements indicating action or lack of action

    oai_token-act-pair · gpt-3.5-turbo

    auxiliary verbs indicating action or obligation

    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
    onomy
    -0.74
    arez
    -0.65
    inosaur
    -0.65
    tty
    -0.63
    enser
    -0.63
    ific
    -0.62
    greg
    -0.62
    oru
    -0.62
    ovember
    -0.62
    amus
    -0.62
    POSITIVE LOGITS
     they
    0.90
     anyone
    0.77
     we
    0.74
     he
    0.71
     any
    0.70
     anybody
    0.68
     she
    0.63
     there
    0.63
    actic
    0.61
     commentators
    0.61
    Activations Density 0.112%

    No Known Activations