© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9331
    Prev
    Next
    INDEX
    Explanations

    values expressed in terms of billions, millions, or trillions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to financial figures or monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.69
     Divinity
    -0.64
    frog
    -0.63
    aders
    -0.60
    downs
    -0.58
    igators
    -0.57
    girl
    -0.57
     Dent
    -0.57
    things
    -0.56
    rament
    -0.56
    POSITIVE LOGITS
     billion
    1.15
    -$
    1.14
    billion
    1.03
     million
    1.00
     Billion
    0.99
    million
    0.99
     trillion
    0.96
    bn
    0.92
     USD
    0.89
     lakh
    0.87
    Activations Density 0.064%

    No Known Activations