© 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. 17864
    Prev
    Next
    INDEX
    Explanations

    phrases related to resolving or figuring out a situation or problem

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions of sorting or organizing

    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
    anton
    -0.62
    images
    -0.61
    NEWS
    -0.61
    ãĥĥãĤ¯
    -0.61
    yg
    -0.59
    obal
    -0.59
    tips
    -0.57
    åº
    -0.57
    jing
    -0.56
    Spread
    -0.56
    POSITIVE LOGITS
    Ħ¢
    0.73
     cheaply
    0.72
    stairs
    0.67
     territ
    0.65
    washer
    0.63
     individually
    0.62
    atis
    0.62
    fires
    0.62
    ender
    0.61
     Mississ
    0.61
    Activations Density 0.120%

    No Known Activations