© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11211
    Prev
    Next
    INDEX
    Explanations

    instances of words relating to hidden traps or deceptiveness

    oai_token-act-pair · gpt-3.5-turbo

    slang or derogatory terms referring to certain types of people or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ienced
    -0.77
    inel
    -0.74
    Interstitial
    -0.73
     tert
    -0.72
    ictional
    -0.71
    itia
    -0.71
    oulos
    -0.70
    inic
    -0.70
    icity
    -0.69
    iate
    -0.68
    POSITIVE LOGITS
    ards
    0.97
    ARDS
    0.92
    housing
    0.92
    loads
    0.89
    arding
    0.87
    load
    0.85
    hop
    0.84
    list
    0.84
    lists
    0.83
    funding
    0.79
    Activations Density 0.243%

    No Known Activations