Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 18860
    Prev
    Next
    INDEX
    Explanations

    terms related to legitimacy

    oai_token-act-pair · gpt-3.5-turbo

    the concept of legitimacy or valid authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hani
    -0.92
    azel
    -0.75
    draw
    -0.72
    rix
    -0.71
     Carbuncle
    -0.70
    ocket
    -0.70
     Coat
    -0.70
    ilan
    -0.69
    berries
    -0.68
     Daniels
    -0.67
    POSITIVE LOGITS
    itimate
    1.08
     legitimate
    0.88
    tarian
    0.73
    soDeliveryDate
    0.70
    DonaldTrump
    0.69
    acies
    0.69
     guiActiveUn
    0.69
    ²¾
    0.68
     reason
    0.67
     sounding
    0.67
    Activations Density 0.009%

    No Known Activations