© 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. 7-RES-JB
    11. 12623
    Prev
    Next
    INDEX
    Explanations

    verbs related to creating or establishing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" related to various entities or creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingly
    -0.73
     behold
    -0.69
    fulness
    -0.68
     whenever
    -0.67
     besides
    -0.66
     held
    -0.66
     enjoying
    -0.66
     suppose
    -0.66
     somebody
    -0.66
    hus
    -0.64
    POSITIVE LOGITS
     requisite
    1.17
    ses
    1.10
     groundwork
    1.07
     aforementioned
    1.05
     entirety
    1.03
     largest
    1.01
     toughest
    0.97
     latter
    0.97
     latest
    0.96
     strongest
    0.94
    Activations Density 0.302%

    No Known Activations