© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    large sums of money mentioned as financial figures

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    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
     boun
    -0.78
     decor
    -0.65
     Valent
    -0.63
     twe
    -0.63
     encl
    -0.62
     moderator
    -0.60
     melt
    -0.60
     usher
    -0.60
     Ãľ
    -0.60
     scaven
    -0.60
    POSITIVE LOGITS
    330
    1.20
    3
    1.18
    9
    1.17
    1
    1.16
    930
    1.14
    0
    1.14
    7
    1.14
    6
    1.14
    4
    1.14
    916
    1.13
    Activations Density 0.071%

    No Known Activations