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. 8279
    Prev
    Next
    INDEX
    Explanations

    phrases involving complex and serious topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that signify a connection or addition in a context of significance

    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
    ESE
    -0.77
     Pigs
    -0.76
    æĥ
    -0.74
    éŃĶ
    -0.72
    olver
    -0.70
    Ĥİ
    -0.69
    ulkan
    -0.68
    ojure
    -0.67
    IRT
    -0.66
     VIDEOS
    -0.65
    POSITIVE LOGITS
    rogen
    1.01
    rogens
    0.96
     therefore
    0.89
     consequently
    0.79
     thus
    0.78
    adic
    0.76
     possibly
    0.76
     hence
    0.70
    chard
    0.68
     inclusive
    0.66
    Activations Density 0.241%

    No Known Activations