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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2462
    Prev
    Next
    INDEX
    Explanations

    dates expressed in a month-day format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrut
    -0.68
    hetically
    -0.61
     minimized
    -0.59
    icable
    -0.57
     fielded
    -0.56
     unintended
    -0.55
     outlawed
    -0.54
     ducks
    -0.54
     Polk
    -0.54
     Connie
    -0.53
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.92
    mph
    0.86
    tenance
    0.84
    BIT
    0.80
    =~=~
    0.77
    ORPG
    0.76
    oldemort
    0.75
    ths
    0.72
    cffff
    0.71
     mph
    0.70
    Activations Density 0.083%

    No Known Activations