© 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. 4-RES-JB
    11. 9219
    Prev
    Next
    INDEX
    Explanations

    words related to official documents, protocol, and authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "D" in various contexts, often related to diagnoses or classifications

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

    No Comments

    Negative Logits
    éĹĺ
    -0.81
    ãĤ¡
    -0.76
     Io
    -0.66
     cov
    -0.66
    zai
    -0.65
     Remem
    -0.64
    ItemTracker
    -0.63
     Bulg
    -0.62
     Nun
    -0.62
    ppo
    -0.62
    POSITIVE LOGITS
    etermin
    1.08
    etermination
    1.06
    ividual
    1.06
    ynam
    1.03
    iscovery
    1.03
    imensional
    1.02
    etermined
    0.98
    ictionary
    0.97
    REAM
    0.97
    ollar
    0.97
    Activations Density 0.033%

    No Known Activations