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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14543
    Prev
    Next
    INDEX
    Explanations

    instances where "other" is specified with a numeral (e.g., "seven other cities")

    oai_token-act-pair · gpt-3.5-turbo

    references to "other" entities or items in a context

    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
    ctor
    -0.80
    ister
    -0.76
     Kuh
    -0.70
    ensibly
    -0.66
    hod
    -0.65
     ç¥ŀ
    -0.63
    ï¸
    -0.63
    ãĥ«
    -0.62
    jo
    -0.62
    hene
    -0.61
    POSITIVE LOGITS
    worldly
    1.55
    quickShipAvailable
    0.85
    sheets
    0.79
     factors
    0.79
     countries
    0.79
     avenues
    0.76
     outlets
    0.75
     kindred
    0.74
     jurisdictions
    0.72
     aspects
    0.72
    Activations Density 0.041%

    No Known Activations