© 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. 7-RES-JB
    11. 21576
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name 'Mone'

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lished
    -0.92
    lishes
    -0.84
    rador
    -0.81
    ickr
    -0.81
    ruary
    -0.77
    rawler
    -0.75
    ournal
    -0.74
    anooga
    -0.73
    mingham
    -0.73
    achusetts
    -0.72
    POSITIVE LOGITS
    gger
    1.08
    xus
    0.88
    llo
    0.84
    lla
    0.81
    gas
    0.80
     Tone
    0.80
    lihood
    0.79
    lli
    0.78
    xual
    0.76
    cone
    0.76
    Activations Density 0.040%

    No Known Activations