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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3140
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving emails or newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving newsletters or updates in an inbox

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tions
    -0.84
    ivas
    -0.81
    ivities
    -0.73
    ibilities
    -0.71
    kered
    -0.63
    edi
    -0.62
    ctors
    -0.60
     conce
    -0.59
    tenance
    -0.59
    lihood
    -0.59
    POSITIVE LOGITS
     subscribers
    0.87
     inbox
    0.86
    ebin
    0.84
    ãĥīãĥ©
    0.77
    \/\/
    0.71
     fruition
    0.69
     Newsletter
    0.68
     surpr
    0.68
    shock
    0.67
     mailbox
    0.67
    Activations Density 0.145%

    No Known Activations