Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11041
    Prev
    Next
    INDEX
    Explanations

    phrases related to high quality or performance

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of high quality or high-performance items

    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
    ulpt
    -0.71
    uary
    -0.70
    edIn
    -0.69
     Reign
    -0.68
    ADRA
    -0.67
    pty
    -0.67
     Carib
    -0.66
    ¾
    -0.66
    ovie
    -0.66
     Canaver
    -0.65
    POSITIVE LOGITS
    density
    1.11
     density
    1.07
     voltage
    1.06
     dimensional
    1.04
     quality
    1.02
    speed
    1.00
     impedance
    1.00
     throughput
    1.00
     fidelity
    0.97
     intensity
    0.95
    Activations Density 0.089%

    No Known Activations