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. 0-RES-JB
    6. 20663
    Prev
    Next
    INDEX
    Explanations

    references to postponement or delays

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and instances of postponement

    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
    pecially
    -0.77
    ghan
    -0.72
    rity
    -0.70
    doms
    -0.70
    rican
    -0.69
     Ally
    -0.69
    bett
    -0.68
     Lys
    -0.66
    ktop
    -0.63
    lus
    -0.63
    POSITIVE LOGITS
    ibu
    2.44
     postpone
    2.01
     aspirin
    2.00
     postponed
    1.58
     postp
    1.53
    hei
    1.51
     Stur
    1.22
     compromises
    1.01
    inventoryQuantity
    0.98
     sunscreen
    0.93
    Activations Density 0.035%

    No Known Activations