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

    Neuronpedia

    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. 13586
    Prev
    Next
    INDEX
    Explanations

    phrases related to purpose or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "point" and expressions related to the relevance or value of actions or concepts

    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
    MpServer
    -0.72
    igree
    -0.70
     strengths
    -0.69
     kindred
    -0.65
     successes
    -0.63
     anecd
    -0.62
     knack
    -0.62
     unsus
    -0.62
    catentry
    -0.62
    clerosis
    -0.60
    POSITIVE LOGITS
     anymore
    1.07
     whatsoever
    0.96
     waste
    0.86
     wasting
    0.85
     nor
    0.80
     anybody
    0.78
     Waste
    0.74
     excuses
    0.74
     EVER
    0.73
    ¿½
    0.72
    Activations Density 0.246%

    No Known Activations