© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    6. 18012
    Prev
    Next
    INDEX
    Explanations

    references to lighting conditions, specifically the term "lit"

    oai_token-act-pair · gpt-3.5-turbo

    references to lighting and illumination in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Premium
    -0.81
    INTER
    -0.69
    ILY
    -0.68
     Armory
    -0.66
    eded
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    BLE
    -0.64
     Commando
    -0.64
    CVE
    -0.64
     Chiefs
    -0.63
    POSITIVE LOGITS
    lit
    1.19
    terness
    1.04
    eral
    1.03
    igation
    0.99
    igated
    0.81
    estial
    0.81
    creen
    0.80
    igators
    0.79
    inct
    0.75
    rodu
    0.73
    Activations Density 0.006%

    No Known Activations