© 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. 11-RES-JB
    11. 20344
    Prev
    Next
    INDEX
    Explanations

    details and uncovering activities related to investigations, uncovering hidden information, and revealing secrets

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to uncovering secrets and investigative journalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gain
    -0.71
    amph
    -0.70
     Reduce
    -0.69
    endment
    -0.68
    equal
    -0.67
    neutral
    -0.67
    accompanied
    -0.66
    meal
    -0.65
    weight
    -0.64
    ĪĴ
    -0.63
    POSITIVE LOGITS
     secrets
    1.79
     workings
    1.44
     secret
    1.37
     mysteries
    1.34
     hidden
    1.32
     truth
    1.26
     truths
    1.25
     depths
    1.18
     backstory
    1.16
     untold
    1.14
    Activations Density 0.433%

    No Known Activations