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. 9-RES-JB
    6. 6522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emon
    -0.68
    ilian
    -0.64
     notions
    -0.62
     supposedly
    -0.62
    phi
    -0.61
    ystem
    -0.61
    Prop
    -0.61
     allegedly
    -0.59
    claim
    -0.59
    urus
    -0.59
    POSITIVE LOGITS
     someday
    0.93
     tomorrow
    0.91
     next
    0.86
     boon
    0.84
     forever
    0.76
    morrow
    0.76
     2019
    0.75
     beneficiary
    0.74
     soon
    0.72
     2020
    0.71
    Activations Density 0.340%

    No Known Activations