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. 3-RES-JB
    6. 22228
    Prev
    Next
    INDEX
    Explanations

    words related to promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    words related to obligations and responsibilities

    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
     Caldwell
    -0.71
     mir
    -0.67
    ushi
    -0.67
     infiltrate
    -0.65
     locality
    -0.63
     burner
    -0.58
    cube
    -0.57
    SEE
    -0.57
    bit
    -0.56
     fortune
    -0.56
    POSITIVE LOGITS
    idth
    1.02
    owed
    0.85
    ield
    0.84
    ielding
    0.76
    itting
    0.74
    orld
    0.74
    NESS
    0.74
    adoes
    0.71
    ness
    0.70
    ows
    0.70
    Activations Density 0.007%

    No Known Activations