© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7632
    Prev
    Next
    INDEX
    Explanations

    personal names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people or public figures, particularly on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ''.
    -0.87
    âĶĢâĶĢ
    -0.76
    ".[
    -0.76
    .).
    -0.75
    .",
    -0.74
    ]."
    -0.74
    ).[
    -0.73
    .ãĢį
    -0.71
    .�
    -0.71
    �
    -0.69
    POSITIVE LOGITS
     @
    1.11
    Jr
    1.05
     Originally
    0.97
     congr
    0.93
     Thanks
    0.87
    steen
    0.87
    afort
    0.84
    why
    0.83
     Yep
    0.83
    _
    0.82
    Activations Density 0.075%

    No Known Activations