© 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. 1-RES-JB
    11. 16370
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to "WE"

    oai_token-act-pair · gpt-3.5-turbo

    references to collective pronouns emphasizing group actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quo
    -0.72
    ussen
    -0.68
    ional
    -0.68
    stood
    -0.68
    ion
    -0.67
    Posts
    -0.62
    iod
    -0.62
    animous
    -0.59
     Pentagon
    -0.59
     Jordanian
    -0.57
    POSITIVE LOGITS
    IRD
    1.19
    WE
    1.10
    ALTH
    1.06
    bsite
    1.01
    FTWARE
    0.93
    YC
    0.91
    ATHER
    0.91
    LL
    0.91
    ldon
    0.89
    ANN
    0.88
    Activations Density 0.007%

    No Known Activations