© 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. 7-RES-JB
    11. 21529
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specialized terms related to business deals or transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to organizational roles and collaborative work environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.75
    teenth
    -0.70
    uba
    -0.70
    metry
    -0.69
    olkien
    -0.69
    NetMessage
    -0.69
     Lumpur
    -0.67
     NOTICE
    -0.67
    EGA
    -0.67
    hered
    -0.64
    POSITIVE LOGITS
    er
    2.59
    ers
    1.98
    ership
    1.82
    ER
    1.34
    erate
    1.31
    erd
    1.29
    ering
    1.29
    erness
    1.28
    eri
    1.27
    ed
    1.21
    Activations Density 0.141%

    No Known Activations