© 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. 7-RES-JB
    11. 23972
    Prev
    Next
    INDEX
    Explanations

    names of prominent figures in news and politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names and political references related to news coverage

    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
    osphere
    -0.98
    anguage
    -0.92
    ologies
    -0.86
    istries
    -0.82
    vertisement
    -0.81
    ocrine
    -0.80
    istic
    -0.80
    aily
    -0.80
    ually
    -0.80
    vironment
    -0.78
    POSITIVE LOGITS
    chio
    0.84
    ARD
    0.69
    rict
    0.69
    minster
    0.69
     Abbey
    0.67
    pants
    0.66
     Isles
    0.64
    velt
    0.63
    arded
    0.63
    isSpecialOrderable
    0.62
    Activations Density 0.071%

    No Known Activations