© 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. 11578
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a group or collective identity

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the verb "to be" in various forms, indicating a state of existence or identity

    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
    odder
    -0.77
    ademic
    -0.71
    iosyncr
    -0.70
    aryl
    -0.70
    rouse
    -0.68
    ulence
    -0.67
    FU
    -0.66
     Rowe
    -0.66
    icist
    -0.65
    rounder
    -0.65
    POSITIVE LOGITS
     ourselves
    1.08
     witnessing
    1.07
     fortunate
    1.00
     thankful
    0.99
     pioneers
    0.98
     talking
    0.98
    avers
    0.93
     lucky
    0.91
     gonna
    0.90
     glad
    0.90
    Activations Density 0.153%

    No Known Activations