© 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. 10-RES-JB
    11. 10647
    Prev
    Next
    INDEX
    Explanations

    mention of flat things or the word "flat" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to flatness or the term "flat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.77
    utra
    -0.75
     warr
    -0.74
     ANGEL
    -0.74
     appropri
    -0.72
    GBT
    -0.71
    EMENT
    -0.70
    ymes
    -0.68
    EStream
    -0.68
    REDACTED
    -0.62
    POSITIVE LOGITS
    ulence
    1.47
    ulent
    1.37
    tered
    1.36
    iron
    1.20
    bread
    1.16
    bed
    1.14
    lining
    1.12
    bush
    1.09
    ters
    1.07
    tering
    1.02
    Activations Density 0.036%

    No Known Activations