© 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. 8-RES-JB
    11. 17592
    Prev
    Next
    INDEX
    Explanations

    keywords related to security and encryption

    oai_token-act-pair · gpt-3.5-turbo

    references to security-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    balls
    -0.76
    è¦ļéĨĴ
    -0.73
     traveller
    -0.70
    lift
    -0.70
    aukee
    -0.69
     bron
    -0.67
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
     Silk
    -0.66
     Gladiator
    -0.65
     Burnett
    -0.65
    POSITIVE LOGITS
    recy
    1.32
    rets
    1.27
    urities
    1.24
    aucus
    1.23
    unia
    1.17
    ular
    1.10
    RET
    1.09
    rete
    1.06
    ured
    1.05
    retion
    1.03
    Activations Density 0.026%

    No Known Activations