© 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. 8-RES-JB
    11. 7840
    Prev
    Next
    INDEX
    Explanations

    words related to interference or meddling in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to interference or disruption of processes and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mail
    -0.62
    ingham
    -0.59
    æµ
    -0.58
    borne
    -0.58
    adobe
    -0.57
    FL
    -0.56
    DragonMagazine
    -0.56
    ãĥª
    -0.56
     aggregation
    -0.55
     Palo
    -0.54
    POSITIVE LOGITS
     extensively
    0.94
     upon
    0.94
     against
    0.90
    aciously
    0.86
    ean
    0.83
     favorably
    0.82
     heavily
    0.81
    antly
    0.79
    ently
    0.79
    uate
    0.79
    Activations Density 0.306%

    No Known Activations