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. 1-RES-JB
    6. 14971
    Prev
    Next
    INDEX
    Explanations

    entities or concepts indicated by '|' characters

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'G', possibly indicating a focus on brands, organizations, or significant terms that begin with "G"

    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
     compr
    -0.77
    ĸļ
    -0.70
     estab
    -0.69
    ĺħ
    -0.68
     htt
    -0.66
    oÄŁ
    -0.63
    terday
    -0.63
     provision
    -0.61
     craw
    -0.61
     crowded
    -0.58
    POSITIVE LOGITS
    roups
    1.07
    uild
    1.02
    RAY
    0.97
    iants
    0.96
    reens
    0.96
    ONE
    0.95
    ossip
    0.94
    AMES
    0.94
    raphic
    0.92
    Ps
    0.91
    Activations Density 0.024%

    No Known Activations