Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8553
    Prev
    Next
    INDEX
    Explanations

    phrases indicating widespread acknowledgment or recognition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "widely" indicating prevalence or common recognition of concepts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cair
    -0.82
    ourke
    -0.81
     Bagg
    -0.79
    ÄŁ
    -0.70
     Keeper
    -0.69
     Element
    -0.66
     Templ
    -0.65
     Ventura
    -0.65
     Aliens
    -0.63
     Timbers
    -0.63
    POSITIVE LOGITS
     regarded
    0.92
    atform
    0.91
     distributed
    0.90
     spaced
    0.89
     dispersed
    0.88
    spread
    0.84
     publicized
    0.83
    entimes
    0.78
    ãĤ©
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.77
    Activations Density 0.010%

    No Known Activations