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. 1-RES-JB
    6. 13779
    Prev
    Next
    INDEX
    Explanations

    Unrelated and random text snippets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term 'Un' followed by a number indicating censorship or uncredited sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.96
     briefs
    -0.74
     cone
    -0.71
     tomat
    -0.69
    anwhile
    -0.69
    代
    -0.65
    azine
    -0.65
     Peb
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
     slopes
    -0.64
    POSITIVE LOGITS
    idad
    0.99
    cles
    0.97
    ortunately
    0.94
    affiliated
    0.90
    classified
    0.87
    ities
    0.86
    stable
    0.86
    usual
    0.85
    Un
    0.85
    ruly
    0.84
    Activations Density 0.006%

    No Known Activations