© 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 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. 6-RES-JB
    11. 12055
    Prev
    Next
    INDEX
    Explanations

    weaknesses or areas lacking in something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to deficiencies or lack in various contexts

    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
    è¦ļéĨĴ
    -0.72
    dr
    -0.69
    escal
    -0.65
     Disp
    -0.62
    flo
    -0.61
    dry
    -0.61
    eds
    -0.60
    pill
    -0.60
    si
    -0.60
    offs
    -0.59
    POSITIVE LOGITS
    lust
    0.93
    luster
    0.92
    avorite
    0.89
     patience
    0.88
     willpower
    0.79
     adequate
    0.77
    ocally
    0.74
     confidence
    0.74
     empathy
    0.73
     specificity
    0.73
    Activations Density 0.027%

    No Known Activations