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. 17813
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 1961 and related events surrounding that time

    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
    hed
    -0.77
    ournals
    -0.73
    econom
    -0.69
    secut
    -0.68
    ipel
    -0.68
    yll
    -0.67
    resp
    -0.67
    hing
    -0.67
    lex
    -0.66
    ulia
    -0.66
    POSITIVE LOGITS
     1962
    1.00
     1963
    0.92
     1956
    0.91
     1958
    0.91
     1957
    0.91
     1959
    0.89
     1961
    0.87
     1965
    0.86
     1954
    0.86
     1955
    0.85
    Activations Density 0.016%

    No Known Activations