© 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. 4-RES-JB
    6. 15782
    Prev
    Next
    INDEX
    Explanations

    the word "lambda"

    oai_token-act-pair · gpt-3.5-turbo

    references to the individual named "Lambo."

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

    No Comments

    Negative Logits
     Occupations
    -0.67
     ISS
    -0.63
    Wan
    -0.61
     Morales
    -0.61
     Hiroshima
    -0.60
     Subtle
    -0.59
    ãģ¦
    -0.59
     Slave
    -0.58
    involved
    -0.58
    Oak
    -0.57
    POSITIVE LOGITS
    borgh
    1.26
    beer
    1.12
    ming
    1.11
    ingo
    1.10
    ydia
    1.04
    orously
    1.03
    inate
    1.01
    pton
    1.00
    inated
    0.99
    mer
    0.98
    Activations Density 0.014%

    No Known Activations