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. 4-RES-JB
    6. 5786
    Prev
    Next
    INDEX
    Explanations

    salutations at the beginning of a correspondence

    oai_token-act-pair · gpt-3.5-turbo

    salutation phrases addressing recipients in letters

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

    No Comments

    Negative Logits
    arian
    -0.73
    itol
    -0.72
    oil
    -0.68
    ucket
    -0.68
    UT
    -0.67
    onom
    -0.66
    ssl
    -0.66
     diver
    -0.66
     foss
    -0.64
    ilingual
    -0.63
    POSITIVE LOGITS
    Dear
    1.16
     Dear
    1.08
     LET
    0.81
    acters
    0.78
    ths
    0.74
    boys
    0.73
     correspondence
    0.73
     thank
    0.72
     sir
    0.72
     mail
    0.71
    Activations Density 0.009%

    No Known Activations