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. 9-RES-JB
    6. 12095
    Prev
    Next
    INDEX
    Explanations

    references to outdoor natural environments

    oai_token-act-pair · gpt-3.5-turbo

    references to nature and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anus
    -0.59
    bour
    -0.55
    uum
    -0.54
    uran
    -0.54
    aud
    -0.52
    ool
    -0.51
     alarm
    -0.50
    glomer
    -0.50
    371
    -0.50
    haw
    -0.50
    POSITIVE LOGITS
    to
    1.33
     to
    1.33
    To
    1.02
     TO
    1.01
     To
    0.96
     thereto
    0.93
    TO
    0.88
     unto
    0.81
     ta
    0.79
     Nanto
    0.76
    Activations Density 0.202%

    No Known Activations