© 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. 9-RES-JB
    6. 14829
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to specific individuals and actions they perform

    oai_token-act-pair · gpt-3.5-turbo

    subjects and personal pronouns in the text

    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
    ngth
    -0.79
    amaz
    -0.73
    DragonMagazine
    -0.71
    vous
    -0.69
    geries
    -0.67
    agonal
    -0.66
    resa
    -0.65
    heny
    -0.65
    ata
    -0.64
    opl
    -0.64
    POSITIVE LOGITS
     dubbed
    0.97
     promptly
    0.95
     sorely
    0.95
     termed
    0.93
     duly
    0.92
     nicknamed
    0.91
     deemed
    0.90
     subsequently
    0.90
     dearly
    0.88
     deem
    0.87
    Activations Density 0.163%

    No Known Activations