© 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. 3-RES-JB
    11. 18431
    Prev
    Next
    INDEX
    Explanations

    intensity-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to intensity or levels of intensity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nee
    -0.78
    vous
    -0.77
    unes
    -0.75
    rote
    -0.73
    BY
    -0.71
    OTA
    -0.70
    esan
    -0.67
    acent
    -0.67
    isle
    -0.66
    apan
    -0.65
    POSITIVE LOGITS
     intensity
    1.19
    intensity
    0.93
     è£ıè¦ļéĨĴ
    0.91
    terness
    0.82
     sensitivity
    0.79
     escalation
    0.78
    mble
    0.77
    uous
    0.76
     interval
    0.76
     intens
    0.74
    Activations Density 0.012%

    No Known Activations