© 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. 14085
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of majority or most

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe relationships or quantities associated with "most of" or "majority of."

    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
    haps
    -0.74
    ²¾
    -0.72
     pse
    -0.68
     Psychiat
    -0.60
     reviewer
    -0.60
     certific
    -0.59
    icion
    -0.58
    gnu
    -0.58
     Solitaire
    -0.57
     notwithstanding
    -0.57
    POSITIVE LOGITS
    tein
    0.89
    æ©
    0.71
    ãĤ¤ãĥĪ
    0.69
    ãĥĢ
    0.69
    ussian
    0.69
    ãĥ³
    0.68
    ãĥª
    0.66
    ãĤ£
    0.66
    ãģĨ
    0.65
    BuyableInstoreAndOnline
    0.64
    Activations Density 0.158%

    No Known Activations