© 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. 7-RES-JB
    11. 1902
    Prev
    Next
    INDEX
    Explanations

    emphasized phrases conveying strong emotions or extremities of situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "utter" and its variations, often indicating a state of failure or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OHN
    -0.80
    iewicz
    -0.79
    llah
    -0.76
    actionDate
    -0.72
    ////
    -0.70
    Æ
    -0.70
    xual
    -0.68
    pei
    -0.67
    atell
    -0.67
     Feder
    -0.67
    POSITIVE LOGITS
    ances
    1.24
    ance
    1.20
    most
    0.93
    ing
    0.86
     amaz
    0.85
    aneous
    0.84
    ancing
    0.83
    ables
    0.81
    ability
    0.79
    ness
    0.79
    Activations Density 0.031%

    No Known Activations