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. 16081
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or associations often related to political or organizational contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific terms related to organizations and their hierarchical structures

    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
     pine
    -0.69
     mortg
    -0.66
     impover
    -0.63
     cran
    -0.63
    ccording
    -0.63
     demol
    -0.62
     dynam
    -0.61
    lov
    -0.60
    chwitz
    -0.60
     irrad
    -0.59
    POSITIVE LOGITS
    orum
    3.57
    imble
    1.34
     Frequency
    1.31
     Fit
    1.27
     Loop
    1.05
     Answers
    1.03
     Sig
    0.97
    Fit
    0.95
    afe
    0.93
    aum
    0.88
    Activations Density 0.029%

    No Known Activations