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. 6370
    Prev
    Next
    INDEX
    Explanations

    phrases related to accepting terms and conditions for receiving updates and offers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate consent or agreement to receive communications

    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
    Bloom
    -0.73
    hop
    -0.69
    rats
    -0.69
    fork
    -0.68
    profits
    -0.67
    gradient
    -0.66
    mania
    -0.66
    hur
    -0.65
     gearing
    -0.62
    Weak
    -0.62
    POSITIVE LOGITS
    ete
    0.77
     abide
    0.75
     receive
    0.72
     accept
    0.71
    asty
    0.70
     Terms
    0.70
     adhere
    0.70
    asse
    0.69
     share
    0.68
     donate
    0.68
    Activations Density 0.029%

    No Known Activations