© 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. 8563
    Prev
    Next
    INDEX
    Explanations

    declarative statements with the word "know" followed by some information or assertion

    oai_token-act-pair · gpt-3.5-turbo

    recurrent phrases asserting knowledge or awareness

    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
    issance
    -0.81
    onding
    -0.80
    isco
    -0.70
    orthy
    -0.69
    phrine
    -0.69
    ermanent
    -0.68
     sidx
    -0.67
     pione
    -0.66
    achus
    -0.65
    aukee
    -0.63
    POSITIVE LOGITS
     firsthand
    1.20
     plenty
    1.02
     how
    1.00
     why
    0.96
     anecd
    0.93
     what
    0.91
     exactly
    0.91
     nothing
    0.90
     lots
    0.89
     many
    0.85
    Activations Density 0.040%

    No Known Activations