© 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. 8-RES-JB
    11. 567
    Prev
    Next
    INDEX
    Explanations

    cooking or baking instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructions or directives for completing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherished
    -0.76
     resurg
    -0.75
     furthe
    -0.71
     valued
    -0.71
     sustained
    -0.71
     neighb
    -0.69
     affirmed
    -0.68
     prized
    -0.68
     condol
    -0.67
     inconsistent
    -0.67
    POSITIVE LOGITS
    Step
    1.27
    STEP
    1.23
    Setup
    1.21
    METHOD
    1.08
    Remove
    1.05
    Install
    1.04
    Method
    1.03
    Begin
    1.01
     Setup
    1.01
    Create
    1.01
    Activations Density 0.364%

    No Known Activations