© 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. 11-RES-JB
    11. 20496
    Prev
    Next
    INDEX
    Explanations

    words related to decrease or downgrade

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'downplaying' or minimizing significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andum
    -0.70
    acca
    -0.66
    ¶ħ
    -0.63
    ë
    -0.60
    OST
    -0.60
    inen
    -0.60
     Kad
    -0.58
    aneous
    -0.58
    arians
    -0.57
    aceous
    -0.57
    POSITIVE LOGITS
    graded
    1.40
    grading
    1.37
    LOAD
    1.30
    played
    1.28
    sized
    1.24
    grades
    1.18
    playing
    1.18
    stairs
    1.15
    pour
    1.14
    hill
    1.12
    Activations Density 0.046%

    No Known Activations