© 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. 22339
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, likely surnames, such as Carroll, Stephenson, Walton, Caldwell

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names, particularly related to individuals and locations

    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
    bsp
    -0.73
     doct
    -0.70
    aciously
    -0.69
     haste
    -0.66
    ariat
    -0.65
    information
    -0.62
    Iraq
    -0.62
    ebus
    -0.62
    ocard
    -0.61
    irements
    -0.60
    POSITIVE LOGITS
     Carroll
    1.22
    sburg
    0.98
    mont
    0.93
    ton
    0.83
    dale
    0.81
     Gardens
    0.80
    ville
    0.77
    oqu
    0.76
     Shelby
    0.75
    anut
    0.75
    Activations Density 0.006%

    No Known Activations