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. 10-RES-JB
    6. 18007
    Prev
    Next
    INDEX
    Explanations

    dates or decades

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades, particularly the 1950s, 1960s, and 1970s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     masc
    -0.61
    aukee
    -0.54
     probing
    -0.54
    venge
    -0.54
    avorite
    -0.53
    DEM
    -0.52
     tonight
    -0.51
    ebus
    -0.51
     Rivals
    -0.48
     ingred
    -0.48
    POSITIVE LOGITS
    s
    1.96
    sie
    1.03
    sburg
    1.00
    si
    0.95
    sis
    0.95
    sat
    0.94
    sand
    0.91
    ties
    0.90
    ies
    0.88
    sg
    0.85
    Activations Density 0.047%

    No Known Activations