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. 4-RES-JB
    6. 23946
    Prev
    Next
    INDEX
    Explanations

    references to butterflies

    oai_token-act-pair · gpt-3.5-turbo

    references to butterflies and related imagery

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

    No Comments

    Negative Logits
    ×Ļ×
    -0.72
    ×ķ
    -0.72
    ensible
    -0.71
    Ô
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
    DN
    -0.70
    gregation
    -0.70
    lying
    -0.69
    RT
    -0.68
    senal
    -0.68
    POSITIVE LOGITS
     butterfly
    1.12
     butterflies
    1.07
    ipop
    0.99
    pillar
    0.96
    flies
    0.92
     Butterfly
    0.88
     lapt
    0.78
     Gardens
    0.77
    pill
    0.76
    apixel
    0.76
    Activations Density 0.021%

    No Known Activations