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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14780
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly names that start with "Ger"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ger" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.82
    uncture
    -0.82
    ãĥ¼ãĥĨãĤ£
    -0.69
    essee
    -0.68
    Constructed
    -0.66
     behold
    -0.66
    piracy
    -0.64
    unct
    -0.63
    ĸļ
    -0.62
     Samoa
    -0.62
    POSITIVE LOGITS
     Ger
    0.94
    bil
    0.86
    anyl
    0.85
    deen
    0.83
    rera
    0.83
    rit
    0.80
    roth
    0.80
    anium
    0.79
    sten
    0.77
    alf
    0.77
    Activations Density 0.003%

    No Known Activations