© 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. 10-RES-JB
    11. 5676
    Prev
    Next
    INDEX
    Explanations

    words related to economic and financial issues

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases involving financial problems and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onica
    -0.78
    Choice
    -0.72
    Lex
    -0.67
    emen
    -0.67
    LES
    -0.66
    Entry
    -0.66
     Explosion
    -0.66
    DAQ
    -0.65
    ava
    -0.64
    ANC
    -0.63
    POSITIVE LOGITS
    etc
    1.25
     etc
    1.20
     otherwise
    0.94
     nurture
    0.89
     engage
    0.86
     ultimately
    0.85
     pray
    0.84
     entertain
    0.82
     dissemin
    0.81
     educate
    0.81
    Activations Density 0.206%

    No Known Activations