© 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. 7811
    Prev
    Next
    INDEX
    Explanations

    phrases related to secrets or confidential information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confide" and its variations

    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
    ï¸ı
    -0.81
    Tur
    -0.60
     Roof
    -0.59
     practicable
    -0.58
     hardest
    -0.57
     Towards
    -0.57
    Ô
    -0.57
     Gamb
    -0.56
     Hope
    -0.55
     questioning
    -0.55
    POSITIVE LOGITS
    ederation
    1.42
    essional
    1.36
    luence
    1.35
    etti
    1.25
    eder
    1.24
    lag
    1.20
    ection
    1.18
    lated
    1.14
    idences
    1.12
    lation
    1.11
    Activations Density 0.019%

    No Known Activations