© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 21182
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and their affiliations in the context of social or political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zurich
    -0.74
     Beacon
    -0.71
    osate
    -0.69
     Constantinople
    -0.69
     Munich
    -0.67
     decre
    -0.65
    raltar
    -0.65
     Romania
    -0.65
     Marse
    -0.65
     Lyon
    -0.65
    POSITIVE LOGITS
     Singh
    1.44
     Sharma
    1.39
     Kumar
    1.32
     Rao
    1.24
     Patel
    1.24
     Gupta
    1.23
     Gandhi
    1.12
    bh
    1.12
     Yad
    1.12
     Devi
    1.12
    Activations Density 0.409%

    No Known Activations