© 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. 7-RES-JB
    11. 13457
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating a preference or level of satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and their associated sentiments regarding past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scra
    -0.57
     Environment
    -0.57
     Vine
    -0.57
    uctions
    -0.56
     Fine
    -0.56
    uction
    -0.54
    istries
    -0.54
     Lt
    -0.54
     Superior
    -0.54
     retri
    -0.54
    POSITIVE LOGITS
    ago
    0.90
     imagined
    0.85
    usual
    0.85
     ever
    0.83
    ":[
    0.81
    ever
    0.75
     usual
    0.75
    immigrant
    0.74
     anticipated
    0.73
     dreamed
    0.72
    Activations Density 0.085%

    No Known Activations