© 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. 16568
    Prev
    Next
    INDEX
    Explanations

    details or descriptions of various reports and statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic reports and data

    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
     Oath
    -0.74
     Prepar
    -0.70
     Compan
    -0.68
     oath
    -0.68
     ceremon
    -0.67
     Jinn
    -0.66
     Authorization
    -0.64
    andon
    -0.64
     Mole
    -0.63
     Sut
    -0.63
    POSITIVE LOGITS
    Chart
    1.24
     statistical
    1.19
     trends
    1.19
     skewed
    1.17
     statistic
    1.16
     anecd
    1.15
     statistically
    1.11
     graphs
    1.10
     statistics
    1.09
     trend
    1.09
    Activations Density 0.577%

    No Known Activations