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. 8-RES-JB
    6. 15213
    Prev
    Next
    INDEX
    Explanations

    features, upgrades, local amenities, events, and offerings related to a specific location or establishment

    oai_token-act-pair · gpt-3.5-turbo

    references to new features, updates, and exciting offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odan
    -0.71
    sis
    -0.69
    iot
    -0.68
    onel
    -0.66
    eric
    -0.66
    amus
    -0.65
    eenth
    -0.65
    ahon
    -0.65
    midt
    -0.63
    pez
    -0.63
    POSITIVE LOGITS
     imaginable
    1.18
     goodies
    1.13
     including
    0.94
     ranging
    0.94
     abound
    0.88
     await
    0.88
     awaits
    0.88
     richness
    0.86
     sprinkled
    0.85
     includ
    0.82
    Activations Density 0.472%

    No Known Activations