© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15147
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or situations happening during certain contexts or settings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "a" in various contexts

    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
    rils
    -0.76
    coins
    -0.70
    Ingredients
    -0.70
    ittens
    -0.70
     experimented
    -0.68
    Enjoy
    -0.67
    inson
    -0.67
    Tags
    -0.66
    cair
    -0.65
    /-
    -0.64
    POSITIVE LOGITS
     meeting
    1.08
     briefing
    1.03
     conference
    1.01
     ceremony
    1.00
     presentation
    0.99
     demonstration
    0.94
     session
    0.94
     joint
    0.94
     gathering
    0.93
     seminar
    0.93
    Activations Density 0.134%

    No Known Activations