© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12694
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or groups associated with Nazareth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingly
    -0.71
     Cascade
    -0.68
     Hundred
    -0.65
     Behavioral
    -0.64
     methyl
    -0.62
     Finger
    -0.62
     Canary
    -0.62
     Marble
    -0.61
     Seah
    -0.60
     Saunders
    -0.59
    POSITIVE LOGITS
    areth
    1.28
    ella
    0.98
    amara
    0.94
    ril
    0.91
    uala
    0.91
    bek
    0.90
    arian
    0.89
    are
    0.89
    algia
    0.88
    ca
    0.86
    Activations Density 0.047%

    No Known Activations