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. 3-RES-JB
    6. 8671
    Prev
    Next
    INDEX
    Explanations

    dates from the early 1960s

    oai_token-act-pair · gpt-3.5-turbo

    specific years, particularly from the 1960s and late 1950s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hed
    -0.88
    ipel
    -0.71
    tro
    -0.70
    unders
    -0.69
    ournals
    -0.69
    lying
    -0.68
    lex
    -0.68
    amn
    -0.67
    ittee
    -0.66
     entirety
    -0.66
    POSITIVE LOGITS
    å¹
    0.89
     onwards
    0.76
     1962
    0.75
    ĸļ
    0.73
    -'
    0.72
    1968
    0.71
     1958
    0.70
    1966
    0.70
     1965
    0.68
     1963
    0.68
    Activations Density 0.028%

    No Known Activations