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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 956
    Prev
    Next
    INDEX
    Explanations

    words related to computer memory such as "ram" and actions related to intensively learning or studying such as "cram"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the words "ram," "cram," "gum," and "tampered."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Test

    No Comments

    Negative Logits
     Cind
    -0.75
     Vald
    -0.73
     Bind
    -0.68
     Knight
    -0.68
    ACP
    -0.67
    terday
    -0.64
    CLASSIFIED
    -0.64
    Ô
    -0.63
    IELD
    -0.63
     Acqu
    -0.63
    POSITIVE LOGITS
    ming
    1.21
     ram
    0.94
    bling
    0.90
    matical
    0.86
    matically
    0.86
    ulus
    0.84
    azon
    0.83
    disk
    0.82
    orously
    0.81
     wrench
    0.81
    Activations Density 0.052%

    No Known Activations