© 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. 0-RES-JB
    6. 11987
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a person named 'arry'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Barry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     psy
    -0.75
     temp
    -0.72
     priority
    -0.70
     higher
    -0.69
     top
    -0.68
     confidence
    -0.66
     myth
    -0.65
     tops
    -0.64
     Tus
    -0.63
     pleasure
    -0.63
    POSITIVE LOGITS
    arry
    4.52
    arr
    1.31
    arl
    1.14
    onduct
    1.09
    arrow
    1.06
    arily
    1.02
    ARY
    1.02
    arrell
    0.98
    ARR
    0.96
    arre
    0.96
    Activations Density 0.012%

    No Known Activations