Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3780
    Prev
    Next
    INDEX
    Explanations

    key words related to computer software and technology, specifically focusing on file formats and computer programming terms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or specific codes related to technology and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nature
    -0.77
     Accountability
    -0.74
    士
    -0.73
    EVA
    -0.73
     Gamble
    -0.69
    è¦ļéĨĴ
    -0.69
     Chaser
    -0.69
    Downloadha
    -0.66
     Seah
    -0.66
    ingham
    -0.65
    POSITIVE LOGITS
    umen
    1.00
    mble
    0.95
    anium
    0.91
    gment
    0.84
    umin
    0.81
    pex
    0.80
    cean
    0.79
    ub
    0.78
    moil
    0.77
    imet
    0.76
    Activations Density 0.195%

    No Known Activations