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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 4679
    Prev
    Next
    INDEX
    Explanations

    mentions of privileges or privileged status

    oai_token-act-pair · gpt-3.5-turbo

    references to privilege

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harvest
    -0.70
     Lighting
    -0.67
    glers
    -0.65
     Alchemy
    -0.64
     pickups
    -0.63
    atoon
    -0.63
     Lash
    -0.62
     Animated
    -0.62
    zyme
    -0.62
    NH
    -0.62
    POSITIVE LOGITS
     privileged
    3.75
    priv
    2.62
     privilege
    2.43
     privileges
    2.36
     Priv
    2.18
    Priv
    2.05
    ileged
    2.00
    ilege
    1.60
     priv
    1.56
     advant
    1.14
    Activations Density 0.026%

    No Known Activations