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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23441
    Prev
    Next
    INDEX
    Explanations

    natural landscapes and outdoor locations characterized by grass, trees, lakes, rocks, mountains, and other nature elements

    oai_token-act-pair · gpt-3.5-turbo

    elements related to natural landscapes and rural settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CTV
    -0.91
     Patron
    -0.82
    ticket
    -0.82
    actionDate
    -0.79
     EDITION
    -0.77
    TeX
    -0.76
    IU
    -0.73
    Tickets
    -0.72
    agonist
    -0.72
    MSN
    -0.71
    POSITIVE LOGITS
     forests
    1.75
     valleys
    1.70
     hills
    1.63
     woodland
    1.61
     bushes
    1.58
     cliffs
    1.58
     grass
    1.57
     forest
    1.54
     trees
    1.54
     mountains
    1.52
    Activations Density 0.350%

    No Known Activations