© 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. 9-RES-JB
    11. 15568
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving a specific desired effect or outcome

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technical processes and effectiveness in achieving desired outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Journals
    -0.79
     Methodist
    -0.74
     Networks
    -0.71
     Ezek
    -0.69
    agents
    -0.69
     preceded
    -0.68
     journals
    -0.67
     prophets
    -0.67
     trolls
    -0.67
     pastors
    -0.66
    POSITIVE LOGITS
     versatility
    1.15
     smooth
    1.06
     impression
    1.05
     smoother
    1.05
     tactile
    1.03
     optimum
    1.03
     consistency
    1.01
     effect
    1.00
     seamless
    1.00
     desired
    1.00
    Activations Density 0.445%

    No Known Activations