Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24478
    Prev
    Next
    INDEX
    Explanations

    words related to physical removal or displacement

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to removal or exclusion

    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
     suff
    -0.65
     conscience
    -0.64
     fare
    -0.64
     Gn
    -0.62
     gn
    -0.61
     fortune
    -0.60
     muse
    -0.60
     slave
    -0.59
     excuse
    -0.59
     Prof
    -0.59
    POSITIVE LOGITS
    oval
    4.92
    oving
    1.34
    oves
    1.17
    irez
    1.06
    rosso
    1.05
    OV
    1.04
    ove
    1.03
    ov
    1.01
    alez
    0.97
    arel
    0.93
    Activations Density 0.004%

    No Known Activations