© 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. 1-RES-JB
    11. 24326
    Prev
    Next
    INDEX
    Explanations

    verbs related to significant change or improvement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "transform" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LIMITED
    -0.74
    Ö¼
    -0.70
    ramid
    -0.63
    olla
    -0.63
     brow
    -0.63
    xia
    -0.63
    akening
    -0.62
    PLIED
    -0.61
     tread
    -0.60
    ello
    -0.59
    POSITIVE LOGITS
     transform
    1.23
     transforms
    1.03
    atile
    0.99
     transformations
    0.95
    ational
    0.91
     transforming
    0.90
    ĸļ
    0.90
     transformation
    0.84
     transformed
    0.83
    ãĥĥ
    0.82
    Activations Density 0.014%

    No Known Activations