© 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. 7-RES-JB
    11. 1541
    Prev
    Next
    INDEX
    Explanations

    technical terms in a text, especially related to IT and finance

    oai_token-act-pair · gpt-3.5-turbo

    references to audio-related content and technical discussions

    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
     })
    -0.68
     )]
    -0.66
    Merit
    -0.65
     PID
    -0.62
     IMAGES
    -0.61
    DAQ
    -0.59
     Replay
    -0.59
     Written
    -0.59
     FML
    -0.58
    NYSE
    -0.58
    POSITIVE LOGITS
    etheless
    1.07
    cellaneous
    0.94
     thereafter
    0.89
     versa
    0.87
     thereto
    0.84
     consequ
    0.83
     accordingly
    0.81
    ogether
    0.78
     assorted
    0.78
     thereof
    0.77
    Activations Density 1.026%

    No Known Activations