© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 4777
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Pro"

    oai_token-act-pair · gpt-3.5-turbo

    references to the organization "Pro Publica."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.74
    ELF
    -0.66
     specificity
    -0.63
     Remastered
    -0.62
     doom
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
     spoon
    -0.59
     numb
    -0.58
     inacc
    -0.58
     halls
    -0.57
    POSITIVE LOGITS
    posal
    1.37
    clamation
    1.32
    ducers
    1.32
    secution
    1.29
    verbs
    1.27
    gres
    1.25
    hibited
    1.22
    digy
    1.17
    portion
    1.16
    zac
    1.13
    Activations Density 0.011%

    No Known Activations