© 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. 8-RES-JB
    11. 4150
    Prev
    Next
    INDEX
    Explanations

    mentions of important or significant positions, such as "prime minister."

    oai_token-act-pair · gpt-3.5-turbo

    references to "prime" as it relates to important or significant events or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.90
    anwhile
    -0.75
    oldemort
    -0.72
     Schwar
    -0.70
    urrencies
    -0.67
     Syndrome
    -0.66
    erves
    -0.65
    arettes
    -0.65
     Polo
    -0.65
     Soup
    -0.64
    POSITIVE LOGITS
    val
    1.06
    knit
    1.04
     ministerial
    0.97
    etime
    0.87
     minister
    0.86
    iary
    0.80
    time
    0.75
     ministers
    0.75
    ises
    0.72
    iaries
    0.71
    Activations Density 0.015%

    No Known Activations