© 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. 11302
    Prev
    Next
    INDEX
    Explanations

    facts or claims regarding events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal issues or allegations involving denial and confirmation

    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
    ktop
    -0.85
     temptation
    -0.81
    venge
    -0.77
     tempt
    -0.77
     pleasures
    -0.74
     crave
    -0.73
     itch
    -0.72
    opian
    -0.71
     goodbye
    -0.70
     patience
    -0.69
    POSITIVE LOGITS
    facts
    1.16
     debunked
    1.12
     contradicted
    1.09
     testified
    1.05
     lied
    1.04
     untrue
    1.01
     Facts
    1.00
     contradicts
    0.97
     FALSE
    0.97
     Fact
    0.97
    Activations Density 0.749%

    No Known Activations