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. 4177
    Prev
    Next
    INDEX
    Explanations

    mentioned words related to messaging or communication platforms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "messaging."

    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
    arte
    -0.77
    engeance
    -0.73
    \/\/
    -0.71
    eln
    -0.70
    bor
    -0.69
    biased
    -0.69
    arson
    -0.68
    vol
    -0.66
    ================================================================
    -0.65
    ft
    -0.64
    POSITIVE LOGITS
     messaging
    1.28
     messages
    0.97
     Messages
    0.88
     goodbye
    0.84
     message
    0.82
    Message
    0.78
    tons
    0.78
     inbox
    0.75
     advis
    0.74
     calculator
    0.73
    Activations Density 0.011%

    No Known Activations