© 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. 7-RES-JB
    11. 23875
    Prev
    Next
    INDEX
    Explanations

    statistical correlations and associations between different variables

    oai_token-act-pair · gpt-3.5-turbo

    statistical correlations related to health and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIDEO
    -0.86
    gart
    -0.71
    ç«
    -0.70
    ãĥīãĥ©
    -0.70
     nerves
    -0.69
    ufact
    -0.68
    chu
    -0.68
     vows
    -0.67
     Slov
    -0.66
     Kits
    -0.65
    POSITIVE LOGITS
     coefficient
    1.31
     coefficients
    1.25
     correlations
    1.09
     inverse
    1.05
     correlation
    1.04
     statistical
    1.02
     predictor
    1.00
     regress
    1.00
     heterogeneity
    1.00
    ogeneity
    0.99
    Activations Density 0.279%

    No Known Activations