© 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. 6-RES-JB
    11. 12146
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a lack of concern or indifference towards certain topics or situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of indifference or apathy towards various topics

    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
    oward
    -0.73
    PG
    -0.71
    scripts
    -0.69
    arist
    -0.69
    visor
    -0.68
    ciplinary
    -0.66
    uns
    -0.66
    Fig
    -0.66
    Pacific
    -0.66
    idelines
    -0.66
    POSITIVE LOGITS
     anymore
    1.32
     whatsoever
    1.03
     necessarily
    0.81
     nor
    0.76
     anybody
    0.74
     any
    0.71
     anything
    0.71
     blinking
    0.70
     EVER
    0.68
     slightest
    0.67
    Activations Density 0.075%

    No Known Activations