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. 8-RES-JB
    6. 18063
    Prev
    Next
    INDEX
    Explanations

    titles or positions within a company along with the word "senior" or "managing"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and senior positions in organizations

    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
    NetMessage
    -0.73
     Pastebin
    -0.67
    iasm
    -0.67
    rums
    -0.67
    ONES
    -0.66
     sockets
    -0.65
    elight
    -0.64
    rained
    -0.63
    abouts
    -0.63
    AAF
    -0.63
    POSITIVE LOGITS
     editor
    1.29
     director
    1.21
     curator
    1.12
     coordinator
    1.11
     administrator
    1.09
     adviser
    1.08
     advisor
    1.06
     assistant
    1.05
     associate
    1.05
    director
    1.04
    Activations Density 0.163%

    No Known Activations