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

    Neuronpedia

    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. 4-RES-JB
    11. 17145
    Prev
    Next
    INDEX
    Explanations

    words related to the company "Unt"

    oai_token-act-pair · gpt-3.5-turbo

    the specific term "Suntory" repeatedly mentioned in various contexts

    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
    ħĭ
    -0.84
     è£ıç
    -0.82
    jri
    -0.80
    izoph
    -0.78
     largeDownload
    -0.73
    isSpecialOrderable
    -0.71
    pter
    -0.70
    76561
    -0.70
    £ı
    -0.70
    Ö¼
    -0.69
    POSITIVE LOGITS
    aneously
    1.06
    itled
    0.96
    aneous
    0.96
    ouched
    0.95
    iful
    0.92
    ifully
    0.91
    ainted
    0.86
    reated
    0.84
    itude
    0.83
    nesses
    0.83
    Activations Density 0.010%

    No Known Activations