© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5275
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to issuing or announcing decisions or notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roots
    -0.76
    ovy
    -0.74
    hov
    -0.74
    tes
    -0.73
    rous
    -0.71
    iterator
    -0.70
    tsky
    -0.69
    anny
    -0.68
    pac
    -0.67
    á½
    -0.67
    POSITIVE LOGITS
     subpoen
    1.20
     warnings
    1.06
     advis
    1.00
     summons
    0.99
     refunds
    0.95
     directives
    0.94
     citations
    0.94
     statements
    0.93
     invitations
    0.92
     orders
    0.92
    Activations Density 0.036%

    No Known Activations