© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22134
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific individuals' names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    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
     plates
    -0.60
     Poles
    -0.57
     Belg
    -0.55
     brill
    -0.54
     youngsters
    -0.53
     Helsinki
    -0.53
     Centauri
    -0.53
    abouts
    -0.52
    ":[{"
    -0.52
     Selection
    -0.52
    POSITIVE LOGITS
     Jr
    0.94
    chuk
    0.82
    houn
    0.79
    aga
    0.78
    baugh
    0.77
    owicz
    0.75
    anse
    0.74
    athan
    0.73
    orge
    0.69
    hammad
    0.68
    Activations Density 0.240%

    No Known Activations