© 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. 10-RES-JB
    11. 5365
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    references to food, consumer products, and service conditions

    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
    éĩ
    -0.60
    leaning
    -0.58
    ffield
    -0.58
    ahime
    -0.58
    urdy
    -0.57
    anmar
    -0.57
    versely
    -0.57
     Bowen
    -0.56
    eday
    -0.55
     Unified
    -0.55
    POSITIVE LOGITS
     whatsoever
    1.89
     nor
    1.54
     anymore
    1.35
     anywhere
    1.11
    nor
    1.09
     except
    1.04
     EVER
    1.03
     detectable
    0.94
     slightest
    0.91
    soever
    0.90
    Activations Density 0.263%

    No Known Activations