© 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. 21907
    Prev
    Next
    INDEX
    Explanations

    words related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    references to writing implements

    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
     disparate
    -0.76
     uninterrupted
    -0.68
     saturation
    -0.63
     affili
    -0.63
     choke
    -0.62
     square
    -0.62
     Myanmar
    -0.62
     discrete
    -0.62
    ebus
    -0.62
     concentrated
    -0.61
    POSITIVE LOGITS
    ennis
    0.77
    laughter
    0.76
    ems
    0.76
    ufact
    0.72
    iak
    0.70
    pelled
    0.69
    acon
    0.68
    orpor
    0.67
    ail
    0.67
    gage
    0.66
    Activations Density 0.000%

    No Known Activations