© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    phrases related to titles, such as movie titles, book titles, or news article titles

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote connections or relationships between entities

    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
     superf
    -0.72
     arrivals
    -0.68
     chem
    -0.68
     aft
    -0.68
     concessions
    -0.67
     annexed
    -0.67
     strikers
    -0.67
     detriment
    -0.66
     breaker
    -0.66
     point
    -0.66
    POSITIVE LOGITS
    selves
    1.18
    itialized
    1.09
     Them
    1.08
     Us
    0.94
     Than
    0.88
     Its
    0.87
     Each
    0.87
     Himself
    0.85
    slaught
    0.84
     Their
    0.83
    Activations Density 0.217%

    No Known Activations