© 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. 8-RES-JB
    11. 23687
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to financial gains and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to financial gains and savings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sshd
    -0.70
     âĺħ
    -0.67
    ptin
    -0.66
    ä¸ī
    -0.66
     Alma
    -0.65
     womb
    -0.64
    gel
    -0.64
    ãĥ¯ãĥ³
    -0.64
    senal
    -0.62
    CLOSE
    -0.60
    POSITIVE LOGITS
    esville
    1.01
    rates
    0.80
    nings
    0.80
    iture
    0.79
    fulness
    0.78
     earners
    0.77
    eful
    0.77
     Taxes
    0.76
     taxes
    0.74
     attributable
    0.74
    Activations Density 0.069%

    No Known Activations