© 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. 21728
    Prev
    Next
    INDEX
    Explanations

    words related to the media

    oai_token-act-pair · gpt-3.5-turbo

    referenced discussions regarding the media and its role in society

    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
     Pis
    -0.72
    20439
    -0.71
    İĭ
    -0.70
    0000000000000000
    -0.70
    perm
    -0.70
    alis
    -0.67
    imov
    -0.66
    nants
    -0.66
    ovi
    -0.65
    ensions
    -0.63
    POSITIVE LOGITS
     outlets
    1.41
    eval
    1.33
     outlet
    1.26
     coverage
    1.20
     circus
    1.12
     mogul
    1.08
     portrayal
    1.07
     blackout
    1.06
     frenzy
    1.05
     mog
    1.04
    Activations Density 0.054%

    No Known Activations