© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    monetary values expressed in thousands or millions

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and monetary values

    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
    actionDate
    -0.73
    heastern
    -0.63
    rina
    -0.63
    versible
    -0.58
    Leod
    -0.56
     Feder
    -0.56
    leased
    -0.55
    activ
    -0.55
    eston
    -0.55
    hran
    -0.55
    POSITIVE LOGITS
    +,
    1.10
    +
    1.05
    +)
    1.04
    +.
    1.03
     apiece
    1.00
     increments
    0.97
    -$
    0.87
     hindsight
    0.82
    /$
    0.82
    plus
    0.78
    Activations Density 0.396%

    No Known Activations