© 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. 2-RES-JB
    11. 23670
    Prev
    Next
    INDEX
    Explanations

    words related to financial institutions or investment ratings

    oai_token-act-pair · gpt-3.5-turbo

    references to the "BB" rating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bourg
    -0.86
    ources
    -0.82
    izations
    -0.80
    inen
    -0.78
    izational
    -0.76
    ãĥ´ãĤ¡
    -0.76
     partName
    -0.74
    ional
    -0.70
    ainment
    -0.70
    perse
    -0.70
    POSITIVE LOGITS
    BB
    1.11
     BB
    1.00
    zeb
    0.84
    JJ
    0.75
    oba
    0.73
    NF
    0.72
    uild
    0.71
    HK
    0.70
    FW
    0.70
    ooth
    0.70
    Activations Density 0.006%

    No Known Activations