© 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. 1-RES-JB
    11. 14255
    Prev
    Next
    INDEX
    Explanations

    phrases related to making changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "amend" and its variations

    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
    zees
    -0.75
     Bears
    -0.73
     Plane
    -0.71
     Famous
    -0.69
    á
    -0.68
     Tycoon
    -0.65
    lar
    -0.64
     Dolphins
    -0.64
     Flying
    -0.64
     Origin
    -0.63
    POSITIVE LOGITS
    terday
    1.09
    ĸļ
    1.04
     amended
    0.95
    xual
    0.87
    ments
    0.86
     amend
    0.86
     thereto
    0.82
    uary
    0.81
    ements
    0.73
     incorpor
    0.72
    Activations Density 0.006%

    No Known Activations