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. 6-RES-JB
    6. 21509
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and rights stated in a constitutional context

    oai_token-act-pair · gpt-3.5-turbo

    references to various constitutional rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAQ
    -0.76
     Clover
    -0.67
    arette
    -0.66
    aco
    -0.65
    arettes
    -0.63
     Remastered
    -0.62
    cit
    -0.62
     srfAttach
    -0.61
    models
    -0.61
     Scream
    -0.61
    POSITIVE LOGITS
    eous
    1.15
    wing
    0.87
     wing
    0.80
     conferred
    0.78
    move
    0.76
    lander
    0.73
     winger
    0.69
     counsel
    0.69
     citizenship
    0.69
     Stuff
    0.69
    Activations Density 0.043%

    No Known Activations