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. 6-RES-JB
    6. 6261
    Prev
    Next
    INDEX
    Explanations

    mentions of natural environments with focus on grass

    oai_token-act-pair · gpt-3.5-turbo

    references to grass in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icts
    -0.72
    osexual
    -0.69
    umbn
    -0.68
     Siem
    -0.68
    iction
    -0.62
     LINK
    -0.61
     Archangel
    -0.61
    andem
    -0.61
     critically
    -0.60
    âĹ¼
    -0.60
    POSITIVE LOGITS
    roots
    1.19
    lands
    1.14
    ho
    1.12
    wood
    1.03
    flower
    0.98
    works
    0.92
    nut
    0.91
    es
    0.91
    banks
    0.91
    fields
    0.90
    Activations Density 0.022%

    No Known Activations