© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start or origin of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "it all" 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
    gee
    -0.80
    limit
    -0.63
     Parables
    -0.62
     Izan
    -0.58
    lication
    -0.57
     Skydragon
    -0.57
    zn
    -0.56
    tis
    -0.56
     Examiner
    -0.56
     Maiden
    -0.56
    POSITIVE LOGITS
    udes
    1.09
    usions
    0.96
    ocation
    0.96
    ayed
    0.94
    ocative
    0.94
    oys
    0.92
    together
    0.92
    uding
    0.88
    ude
    0.86
    ocating
    0.84
    Activations Density 0.042%

    No Known Activations