© 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. 0-RES-JB
    11. 13427
    Prev
    Next
    INDEX
    Explanations

    phrases related to size or degree

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "considerable" along with related terms indicating significant impact or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VS
    -0.64
    FP
    -0.59
     Didn
    -0.58
    ger
    -0.58
    MO
    -0.57
     vs
    -0.57
    ups
    -0.57
    izers
    -0.57
    izer
    -0.56
    ator
    -0.56
    POSITIVE LOGITS
     considerable
    3.11
     immense
    1.71
     tremendous
    1.65
     enormous
    1.46
     substantial
    1.45
     sizeable
    1.44
     ample
    1.42
     considerably
    1.41
     formidable
    1.40
     extensive
    1.40
    Activations Density 0.014%

    No Known Activations