© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11150
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirmation or verification of information

    oai_token-act-pair · gpt-3.5-turbo

    references to confirmation and accuracy in narratives or reports

    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
    ï¸ı
    -0.87
     Lets
    -0.75
    taboola
    -0.74
     âĿ
    -0.74
    ðŁĺ
    -0.73
    \",
    -0.67
    razil
    -0.65
    }}}
    -0.63
     Owner
    -0.62
     ðŁij
    -0.62
    POSITIVE LOGITS
     ostensibly
    0.98
     contempor
    0.91
     precisely
    0.90
     neocons
    0.89
     plainly
    0.88
     Kissinger
    0.87
     Nixon
    0.86
     unamb
    0.86
     Giuliani
    0.85
     postwar
    0.85
    Activations Density 1.322%

    No Known Activations