© 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. 3-RES-JB
    11. 2885
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of coming or arriving

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of "coming with" or associated responsibilities and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.70
    Storage
    -0.67
    tein
    -0.65
    abulary
    -0.65
    esa
    -0.64
    Override
    -0.61
    oyal
    -0.59
    catentry
    -0.58
    syn
    -0.56
    friend
    -0.56
    POSITIVE LOGITS
    furt
    0.81
     blows
    0.70
    retty
    0.69
    hest
    0.69
     Lilly
    0.68
    ocobo
    0.68
     fruition
    0.66
     fray
    0.64
    quest
    0.64
    obin
    0.64
    Activations Density 0.264%

    No Known Activations