Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 4148
    Prev
    Next
    INDEX
    Explanations

    mentions of mailing lists and the act of mailing items

    oai_token-act-pair · gpt-3.5-turbo

    words related to mailing lists and the act of mailing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SEC
    -0.73
    obal
    -0.73
    oti
    -0.72
    Ti
    -0.71
    neutral
    -0.68
    âĵĺ
    -0.66
    anity
    -0.64
    imb
    -0.64
     Kant
    -0.63
    iour
    -0.63
    POSITIVE LOGITS
     mailing
    1.45
     mail
    1.11
     mosqu
    0.94
     mailed
    0.93
     address
    0.88
     newsletters
    0.87
    legram
    0.85
     subscribers
    0.81
     addresses
    0.79
     mailbox
    0.79
    Activations Density 0.004%

    No Known Activations