© 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. 22277
    Prev
    Next
    INDEX
    Explanations

    numbers and data related to financial and economic aspects, such as prices, values, rates, or approvals

    oai_token-act-pair · gpt-3.5-turbo

    economic terms related to insurance and property markets

    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
    sonian
    -0.72
    actory
    -0.70
    nant
    -0.65
    irgin
    -0.65
    rodu
    -0.61
    dit
    -0.58
    acket
    -0.58
    idden
    -0.58
    ixtures
    -0.58
    hem
    -0.58
    POSITIVE LOGITS
     skyrocket
    1.23
     plummeted
    1.22
     soared
    1.20
     soar
    1.09
     plummet
    1.05
     surged
    1.04
     peaked
    1.00
     rose
    0.99
     slump
    0.99
     fluct
    0.98
    Activations Density 0.460%

    No Known Activations