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. 9-RES-JB
    6. 18907
    Prev
    Next
    INDEX
    Explanations

    communications or interactions involving phone calls, voicemails, and messages

    oai_token-act-pair · gpt-3.5-turbo

    references to communication methods and messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bench
    -0.77
    ç¥ŀ
    -0.75
    Scale
    -0.74
    itect
    -0.72
    adiator
    -0.72
    Course
    -0.69
    udo
    -0.67
     Bench
    -0.67
    ¥µ
    -0.67
    advant
    -0.67
    POSITIVE LOGITS
     voic
    1.47
     fax
    1.43
     inbox
    1.36
     Gmail
    1.34
     messages
    1.34
     mail
    1.32
    mail
    1.27
     mailbox
    1.26
    mails
    1.26
     mailed
    1.25
    Activations Density 0.666%

    No Known Activations