© 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. 15991
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and official authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security and secularism

    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
    è¦ļéĨĴ
    -0.69
     Silk
    -0.67
     Gladiator
    -0.67
    balls
    -0.66
     Siberian
    -0.62
     irrit
    -0.61
    ãĥ£
    -0.60
     bron
    -0.60
     Burnett
    -0.59
     Legion
    -0.59
    POSITIVE LOGITS
    recy
    1.57
    rets
    1.54
    urities
    1.40
    ular
    1.34
    aucus
    1.25
    ession
    1.25
    RET
    1.23
    ured
    1.21
    rete
    1.20
    retion
    1.16
    Activations Density 0.024%

    No Known Activations