© 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. 6-RES-JB
    11. 20335
    Prev
    Next
    INDEX
    Explanations

    references to countries joining international organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" as a definite article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    each
    -0.73
     namely
    -0.70
    lets
    -0.70
    worn
    -0.68
    CVE
    -0.66
    strap
    -0.66
    pers
    -0.65
     resorted
    -0.65
    zon
    -0.65
     located
    -0.64
    POSITIVE LOGITS
     fray
    1.26
     same
    1.07
     forefront
    0.95
     ranks
    0.94
     realm
    0.92
     latter
    0.91
     highest
    0.91
     confines
    0.89
     nation
    0.86
     presidency
    0.85
    Activations Density 0.447%

    No Known Activations