© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 18510
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in '-ial'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "partial."

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

    No Comments

    Negative Logits
    Trend
    -0.94
    ħĭ
    -0.81
    ORGE
    -0.79
    ¯¯
    -0.78
    åĤ
    -0.76
    eers
    -0.75
    yers
    -0.75
    orge
    -0.74
    sers
    -0.74
    ould
    -0.72
    POSITIVE LOGITS
     eclipse
    1.03
    ity
    1.02
     agon
    0.84
     partial
    0.77
    iple
    0.76
    ities
    0.72
     eclips
    0.69
     amount
    0.69
     explanation
    0.68
     collateral
    0.68
    Activations Density 0.006%

    No Known Activations