© 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. 4-RES-JB
    11. 17217
    Prev
    Next
    INDEX
    Explanations

    promotional messages encouraging engagement and action

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented commands related to gameplay and interactive activities

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

    No Comments

    Negative Logits
    cffffcc
    -0.79
    terday
    -0.63
     stemming
    -0.62
    rb
    -0.61
    pires
    -0.60
     bureau
    -0.60
     distortion
    -0.60
     plag
    -0.59
    ordered
    -0.59
    atellite
    -0.58
    POSITIVE LOGITS
     Yourself
    0.98
     Your
    0.82
     Them
    0.79
    verning
    0.77
     Cancel
    0.76
     Format
    0.76
     Setup
    0.75
     Ingredients
    0.75
     yourself
    0.74
     Advis
    0.74
    Activations Density 0.227%

    No Known Activations