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. 16049
    Prev
    Next
    INDEX
    Explanations

    references to nature and natural elements

    oai_token-act-pair · gpt-3.5-turbo

    references to nature and its attributes

    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
    oned
    -0.83
    oning
    -0.83
    enger
    -0.81
    UGE
    -0.81
    onest
    -0.74
    oop
    -0.74
    acco
    -0.72
    itone
    -0.71
    nuts
    -0.70
    iken
    -0.70
    POSITIVE LOGITS
     preserves
    0.90
     documentaries
    0.85
     instinct
    0.78
     fiction
    0.78
     reserve
    0.76
     conservation
    0.76
     lover
    0.75
     Conserv
    0.74
     preserve
    0.74
    forms
    0.73
    Activations Density 0.041%

    No Known Activations