© 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. 6140
    Prev
    Next
    INDEX
    Explanations

    words related to the city of Cologne

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Cologne

    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
    arily
    -0.73
    ires
    -0.73
    rew
    -0.71
    arial
    -0.71
    egal
    -0.68
    ally
    -0.67
     carrots
    -0.67
    ortunately
    -0.67
     diagonal
    -0.66
    edIn
    -0.66
    POSITIVE LOGITS
     Cologne
    0.94
    halla
    0.94
    ologne
    0.89
    ibel
    0.88
    borg
    0.79
     Calais
    0.78
     Dunk
    0.71
    ibr
    0.70
    oidal
    0.69
    mberg
    0.69
    Activations Density 0.022%

    No Known Activations