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. 0-RES-JB
    6. 4630
    Prev
    Next
    INDEX
    Explanations

    words related to resigning from positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    the act of resigning from a position or office

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boost
    -0.66
    World
    -0.65
    ME
    -0.63
    TM
    -0.63
     tracking
    -0.63
     track
    -0.63
    jam
    -0.62
    world
    -0.62
    block
    -0.61
    Block
    -0.61
    POSITIVE LOGITS
     resigned
    3.66
     resign
    2.22
     resignation
    2.19
     quit
    1.54
     apologised
    1.32
     withdrew
    1.26
     sacked
    1.25
     disbanded
    1.25
     retired
    1.24
     apologized
    1.24
    Activations Density 0.009%

    No Known Activations