© 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. 10-RES-JB
    11. 12442
    Prev
    Next
    INDEX
    Explanations

    connections or correlations between different factors or variables

    oai_token-act-pair · gpt-3.5-turbo

    references to correlations or links between different variables

    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
    quished
    -0.99
    DragonMagazine
    -0.96
    \\\\\\\\
    -0.93
    ighters
    -0.87
    Reply
    -0.86
    wic
    -0.84
    yssey
    -0.82
    scrib
    -0.82
    »Ĵ
    -0.82
    Catalog
    -0.82
    POSITIVE LOGITS
     obesity
    1.23
     increased
    1.14
     criminality
    1.08
     propensity
    1.05
     exposure
    1.03
     poverty
    1.02
     decreased
    1.02
     ethnicity
    1.01
     susceptibility
    1.00
     elevation
    0.99
    Activations Density 0.101%

    No Known Activations