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. 2-RES-JB
    6. 13042
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking on responsibilities or tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "undertake" and its variations, indicating a focus on actions involving responsibility or initiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Congressman
    -0.67
    lua
    -0.66
    pac
    -0.64
    Enhanced
    -0.64
    room
    -0.64
    corn
    -0.62
    bul
    -0.62
    ping
    -0.61
    akin
    -0.60
     Pupp
    -0.60
    POSITIVE LOGITS
     undertaken
    1.20
     undertake
    1.18
     undertaking
    1.05
     undertook
    0.95
    ĸļ
    0.94
    ngth
    0.85
    TAIN
    0.81
    xual
    0.79
    CLASSIFIED
    0.79
    ĨĴ
    0.78
    Activations Density 0.012%

    No Known Activations