© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2644
    Prev
    Next
    INDEX
    Explanations

    terms related to overheating and surveillance activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and privacy invasion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosity
    -0.80
    ually
    -0.70
    Interstitial
    -0.69
    icals
    -0.66
    ãĥĩ
    -0.66
    ially
    -0.66
    ³³³³³³³³³³³³³³³³
    -0.64
     hereby
    -0.63
    imentary
    -0.63
     Jiu
    -0.62
    POSITIVE LOGITS
    ritten
    1.17
    riter
    1.14
    onduct
    1.12
    inding
    1.12
    atching
    1.08
    ield
    1.08
    apped
    1.08
    aving
    1.07
    uff
    1.07
    arers
    1.06
    Activations Density 0.062%

    No Known Activations