© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 1434
    Prev
    Next
    INDEX
    Explanations

    phrases related to being a significant or central point

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anchor."

    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
    ensation
    -0.85
    INESS
    -0.72
    BLE
    -0.71
    tm
    -0.70
    ordan
    -0.70
    atche
    -0.69
    axies
    -0.69
    OTOS
    -0.68
    enza
    -0.68
    cigarettes
    -0.68
    POSITIVE LOGITS
     anchor
    1.20
     anch
    1.18
     anchors
    1.07
     anchored
    1.06
    orage
    0.94
     tenant
    0.81
     Anch
    0.80
     Canal
    0.74
    ments
    0.73
    ovy
    0.72
    Activations Density 0.004%

    No Known Activations