© 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. 17761
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and rebates

    oai_token-act-pair · gpt-3.5-turbo

    phrases or quotations that express strong sentiments or statements

    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
     Vaugh
    -0.72
     conj
    -0.69
     others
    -0.66
     whipping
    -0.60
     folded
    -0.60
     reprint
    -0.59
    ismo
    -0.58
     mirrors
    -0.58
    aneers
    -0.58
    manship
    -0.58
    POSITIVE LOGITS
    yss
    1.01
    Cause
    0.95
    -'
    0.93
    Interstitial
    0.92
    Mech
    0.86
    affer
    0.84
    cause
    0.84
    taboola
    0.83
     ',
    0.83
    Too
    0.82
    Activations Density 0.026%

    No Known Activations