© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6228
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are likely part of a name (particularly 'Douth' with varying levels of intensity)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "South" in various contexts

    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
     patents
    -0.64
     capsules
    -0.63
     ÃĹ
    -0.62
     Microsoft
    -0.62
     Bungie
    -0.62
     Ike
    -0.61
     NVIDIA
    -0.60
     Boeing
    -0.59
     owned
    -0.59
     âĪ
    -0.59
    POSITIVE LOGITS
    outh
    4.81
    terday
    1.16
    acht
    1.08
    vous
    1.02
    overe
    0.99
    orkshire
    0.96
    aid
    0.95
    omething
    0.94
    antis
    0.92
    auga
    0.92
    Activations Density 0.011%

    No Known Activations