© 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 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. 4183
    Prev
    Next
    INDEX
    Explanations

    phrases or statements related to rights and freedoms

    oai_token-act-pair · gpt-3.5-turbo

    references to rights and entitlements

    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
    trap
    -0.78
    natureconservancy
    -0.72
    wcsstore
    -0.70
    cape
    -0.68
     ILCS
    -0.67
    IONS
    -0.65
     resil
    -0.64
    Bench
    -0.63
    norm
    -0.63
    Edge
    -0.61
    POSITIVE LOGITS
     electors
    0.93
     individuals
    0.91
     persons
    0.85
     mankind
    0.85
     citizens
    0.83
     minorities
    0.82
     humankind
    0.81
     conscience
    0.79
     anyone
    0.78
     peoples
    0.78
    Activations Density 0.128%

    No Known Activations