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. 11908
    Prev
    Next
    INDEX
    Explanations

    years from the 1950s

    oai_token-act-pair · gpt-3.5-turbo

    references to the 1950s decade

    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
    atro
    -0.89
    abol
    -0.74
    unal
    -0.72
    Prem
    -0.71
    kell
    -0.71
    chance
    -0.70
    uid
    -0.69
    acia
    -0.68
    par
    -0.68
    econom
    -0.66
    POSITIVE LOGITS
     1950
    0.88
    sburg
    0.87
    ishers
    0.75
    æ©Ł
    0.73
    å¹
    0.73
    ãĤ¦ãĤ¹
    0.73
     1960
    0.72
     ILCS
    0.72
    eenth
    0.70
    sburgh
    0.70
    Activations Density 0.010%

    No Known Activations