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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 1991
    Prev
    Next
    INDEX
    Explanations

    words related to resignations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resignation" and related concepts of leaving a position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.81
    acca
    -0.71
    ohyd
    -0.70
    prop
    -0.69
    ophon
    -0.68
    rodu
    -0.68
    gran
    -0.68
    MpServer
    -0.68
    rica
    -0.67
    atomic
    -0.66
    POSITIVE LOGITS
     resignation
    0.91
     announcement
    0.83
    isSpecialOrderable
    0.71
     srfAttach
    0.71
    ptin
    0.70
    ylum
    0.69
     inquiry
    0.67
    ishment
    0.67
     pardon
    0.66
     saga
    0.65
    Activations Density 0.021%

    No Known Activations