© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 7070
    Prev
    Next
    INDEX
    Explanations

    dates in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years or dates

    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
    yll
    -0.82
    ongh
    -0.77
     grids
    -0.74
    warts
    -0.73
    reon
    -0.72
    orney
    -0.72
    bor
    -0.71
     ship
    -0.71
     regiment
    -0.70
    pees
    -0.68
    POSITIVE LOGITS
    å¹
    1.29
     Remastered
    0.75
     EDITION
    0.74
    00200000
    0.73
     Reborn
    0.72
     Edition
    0.72
    ãĥ¬
    0.68
     INTER
    0.68
     Reincarn
    0.67
     RELEASE
    0.67
    Activations Density 0.116%

    No Known Activations