© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1082
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgment or evaluation, specifically about something being deemed or considered in a certain way

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the evaluation or judgment of reliability or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrimmage
    -0.74
    ismo
    -0.71
     Debor
    -0.66
    dayName
    -0.61
     Hoy
    -0.60
     Pacers
    -0.60
     Rapp
    -0.60
    ohyd
    -0.58
     Cheong
    -0.58
    details
    -0.57
    POSITIVE LOGITS
    phas
    1.48
     unemploy
    0.89
     deem
    0.89
    EMP
    0.88
     unfit
    0.79
     deemed
    0.79
    pell
    0.78
    lessly
    0.78
    geist
    0.77
     discretion
    0.76
    Activations Density 0.048%

    No Known Activations