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. 9-RES-JB
    6. 715
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and government actions

    oai_token-act-pair · gpt-3.5-turbo

    references to violations of privacy rights and governmental overreach

    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
    cin
    -0.78
    cephal
    -0.73
    abulary
    -0.72
    cific
    -0.72
    oys
    -0.71
     Signs
    -0.71
    erald
    -0.70
    ixture
    -0.70
    estones
    -0.68
     Lamp
    -0.68
    POSITIVE LOGITS
     freedoms
    1.44
     freedom
    1.38
     privacy
    1.30
     liberty
    1.25
    freedom
    1.24
     liberties
    1.22
    Freedom
    1.18
     autonomy
    1.15
     Privacy
    1.12
     rights
    1.10
    Activations Density 0.960%

    No Known Activations