© 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. 4-RES-JB
    11. 10308
    Prev
    Next
    INDEX
    Explanations

    mentions of events or entities involved in intense situations, such as battles or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vy" within various contexts

    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
    ATTLE
    -0.69
    yrinth
    -0.66
    href
    -0.65
    emate
    -0.64
    Tokens
    -0.61
    Contents
    -0.61
    ained
    -0.61
    eared
    -0.60
    Reviewed
    -0.60
     Crus
    -0.60
    POSITIVE LOGITS
    vy
    1.22
    yy
    0.84
    anka
    0.83
    giene
    0.77
     Pry
    0.77
    puff
    0.76
    yk
    0.75
    cture
    0.72
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.70
    Å«
    0.69
    Activations Density 0.012%

    No Known Activations