© 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. 6-RES-JB
    11. 14653
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or organizations containing the word "Center" or "Centro."

    oai_token-act-pair · gpt-3.5-turbo

    recurring segments or patterns in text, particularly those related to the word "center."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.73
    detail
    -0.68
    ighth
    -0.65
    odka
    -0.62
    pedia
    -0.60
     accompan
    -0.60
    isance
    -0.59
    externalActionCode
    -0.59
    ::::::::
    -0.59
    perty
    -0.58
    POSITIVE LOGITS
    arius
    0.81
    ALLY
    0.81
    eele
    0.75
    pole
    0.70
    rist
    0.70
    ierre
    0.70
    loe
    0.69
    Fed
    0.69
    rite
    0.68
     Tend
    0.65
    Activations Density 0.100%

    No Known Activations