© 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. 10-RES-JB
    11. 10115
    Prev
    Next
    INDEX
    Explanations

    words related to music and various entities or concepts such as cameras, robots, and villains

    oai_token-act-pair · gpt-3.5-turbo

    references to movies and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ])
    -0.85
     )))
    -0.84
     )]
    -0.84
     ),
    -0.76
     ));
    -0.75
     ))
    -0.73
    ]),
    -0.72
     ):
    -0.70
    BuyableInstoreAndOnline
    -0.68
    20439
    -0.68
    POSITIVE LOGITS
    .
    1.26
    .?
    1.07
    .:
    0.91
    .;
    0.86
    _.
    0.84
    ./
    0.83
    ._
    0.83
    !.
    0.83
    .(
    0.82
    ."
    0.79
    Activations Density 0.599%

    No Known Activations