© 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. 7068
    Prev
    Next
    INDEX
    Explanations

    the phrase "True" in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "truth"

    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
    ishers
    -0.80
    inson
    -0.74
    Corp
    -0.71
    acco
    -0.69
    kson
    -0.67
    -+-+
    -0.66
    pta
    -0.66
    served
    -0.66
    iture
    -0.65
    uty
    -0.65
    POSITIVE LOGITS
     believer
    1.20
     believers
    1.18
     freshman
    0.84
     positives
    0.82
    crypt
    0.80
    color
    0.78
     colors
    0.77
     patriot
    0.76
     guiIcon
    0.75
     unfocusedRange
    0.74
    Activations Density 0.023%

    No Known Activations