© 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. 9-RES-JB
    11. 14772
    Prev
    Next
    INDEX
    Explanations

    legal or contractual terms related to permissions or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal restrictions and responsibilities

    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
     Roose
    -0.61
    NOW
    -0.61
     Uriel
    -0.60
    stown
    -0.60
    Sand
    -0.59
     squash
    -0.59
     Raven
    -0.59
     Nebula
    -0.58
    ÅŁ
    -0.58
     Centauri
    -0.58
    POSITIVE LOGITS
    ifice
    0.97
    Else
    0.95
     hereafter
    0.93
     otherwise
    0.88
    withstanding
    0.85
    uana
    0.83
     lawful
    0.83
     persons
    0.83
     any
    0.82
     combination
    0.81
    Activations Density 0.154%

    No Known Activations