© 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
    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. 10088
    Prev
    Next
    INDEX
    Explanations

    technical terms related to equipment and systems maintenance

    oai_token-act-pair · gpt-3.5-turbo

    ratings or evaluations related to quality or performance

    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
     elves
    -0.86
     contag
    -0.84
     communists
    -0.84
     aven
    -0.83
    conservancy
    -0.82
     vampires
    -0.80
     samurai
    -0.79
     skelet
    -0.77
     kale
    -0.77
     rainbow
    -0.77
    POSITIVE LOGITS
     Length
    1.49
     Ratio
    1.48
     Capacity
    1.46
     Rate
    1.41
     Detail
    1.39
     Handling
    1.39
     Slot
    1.38
     Feet
    1.38
     Delay
    1.37
     Entry
    1.37
    Activations Density 0.333%

    No Known Activations