Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12514
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases such as "E-B," "C-R-I-M-E-S," "H-E-A-R-S-E-Y," and "Y-i-B" which seem to be unrelated and don't present a common theme

    oai_token-act-pair · gpt-3.5-turbo

    capital letters, particularly the initials of titles or acronyms

    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
    hower
    -0.81
    certain
    -0.64
    interstitial
    -0.61
    govtrack
    -0.60
    enegger
    -0.58
    general
    -0.58
    grave
    -0.58
     velvet
    -0.57
    necess
    -0.56
    MORE
    -0.56
    POSITIVE LOGITS
    BN
    0.83
    OPA
    0.76
    ainer
    0.70
    oldemort
    0.68
    opa
    0.66
     Kenobi
    0.64
    ZE
    0.64
    pai
    0.64
     [&
    0.62
    ternity
    0.62
    Activations Density 0.158%

    No Known Activations