© 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. 1913
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly those related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and organizations, particularly individuals and the CPS (Child Protective Services)

    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
    prus
    -0.75
    lette
    -0.74
    riors
    -0.71
    rylic
    -0.70
    ights
    -0.68
    icious
    -0.66
     grabs
    -0.62
    ctl
    -0.62
    omics
    -0.62
    rise
    -0.61
    POSITIVE LOGITS
    deen
    0.83
     Pengu
    0.82
    arsh
    0.81
     Ans
    0.75
    heim
    0.74
    illon
    0.72
    arette
    0.71
    liam
    0.71
    wered
    0.71
     Spiegel
    0.70
    Activations Density 0.103%

    No Known Activations