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. 9396
    Prev
    Next
    INDEX
    Explanations

    combinations of different factors or components

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe combinations or mixtures of things

    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
    ©¶æ¥µ
    -0.98
    º
    -0.86
    aii
    -0.76
     Caption
    -0.74
    xus
    -0.73
    ª
    -0.72
    yre
    -0.72
    Ĭ
    -0.71
    ı
    -0.70
    keeper
    -0.69
    POSITIVE LOGITS
     sexes
    1.21
     genders
    1.05
     both
    0.94
     genres
    0.93
     styles
    0.88
     disparate
    0.88
     extremes
    0.86
     cultures
    0.82
     factors
    0.82
     oppos
    0.79
    Activations Density 0.128%

    No Known Activations