© 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. 7623
    Prev
    Next
    INDEX
    Explanations

    words related to individuals or entities named "us" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "us."

    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
    regor
    -0.68
    ottest
    -0.67
    ITNESS
    -0.65
    issance
    -0.64
     runoff
    -0.59
    GM
    -0.58
     payoff
    -0.58
    attery
    -0.58
    RAG
    -0.58
    razil
    -0.56
    POSITIVE LOGITS
    pex
    1.14
    peed
    1.09
    sein
    1.08
    chwitz
    1.01
    CRIP
    1.01
    pect
    1.00
    pecting
    0.94
    cular
    0.94
    cules
    0.93
    etts
    0.92
    Activations Density 0.036%

    No Known Activations