© 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. 2-RES-JB
    6. 1850
    Prev
    Next
    INDEX
    Explanations

    instances where something is observed or witnessed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seen"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prime
    -0.77
    vernment
    -0.76
    trap
    -0.71
    angan
    -0.68
    cult
    -0.68
    locked
    -0.64
    atto
    -0.62
    cise
    -0.60
    camp
    -0.60
    plan
    -0.60
    POSITIVE LOGITS
    PsyNetMessage
    0.84
     Seen
    0.82
    dust
    0.81
    seeing
    0.78
    ãĤ¼
    0.78
    agascar
    0.77
    IRT
    0.74
    ../
    0.72
     seen
    0.72
    swick
    0.71
    Activations Density 0.029%

    No Known Activations