© 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. 0-RES-JB
    6. 8033
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location, particularly focusing on the keyword "Wenzhou."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idas
    -0.91
     sermon
    -0.72
     Bristol
    -0.70
     inj
    -0.69
     Auth
    -0.66
     Strauss
    -0.66
     redu
    -0.64
    Zen
    -0.63
     Forbes
    -0.63
     opin
    -0.63
    POSITIVE LOGITS
    hou
    2.67
     Plasma
    1.32
     grandchildren
    1.17
     CGI
    1.16
     plasma
    1.11
     ATM
    1.07
    mbudsman
    0.98
     CG
    0.96
    qv
    0.91
    edo
    0.89
    Activations Density 0.064%

    No Known Activations