© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 10223
    Prev
    Next
    INDEX
    Explanations

    phrases related to authorization or permission

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "authorized" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.79
    Cube
    -0.77
    Unity
    -0.71
     Abyssal
    -0.70
    -----------
    -0.70
    Tool
    -0.69
    kaya
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    ÃŁ
    -0.68
    etus
    -0.68
    POSITIVE LOGITS
     authorized
    1.25
     authorizing
    1.15
     authorize
    1.06
     confir
    1.02
     authorised
    1.01
    authorized
    1.00
     authorization
    0.96
    etheless
    0.82
    Reviewer
    0.81
    merce
    0.79
    Activations Density 0.007%

    No Known Activations