© 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. 6-RES-JB
    11. 19711
    Prev
    Next
    INDEX
    Explanations

    the word "most" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the majority or commonality among groups or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rompt
    -0.92
    heid
    -0.82
    instead
    -0.70
    icer
    -0.69
    alid
    -0.67
    moil
    -0.67
    pload
    -0.64
    thora
    -0.62
    vest
    -0.62
    nton
    -0.61
    POSITIVE LOGITS
     importantly
    0.83
     mornings
    0.73
    body
    0.72
     sane
    0.72
     observers
    0.71
     egreg
    0.71
     superficial
    0.70
    afa
    0.69
    ONE
    0.69
     millenn
    0.67
    Activations Density 0.049%

    No Known Activations