© 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. 4-RES-JB
    11. 6213
    Prev
    Next
    INDEX
    Explanations

    the word "ens" with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ensuring" or related variations

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

    No Comments

    Negative Logits
     hitch
    -0.72
    zzi
    -0.64
     edited
    -0.64
     McAuliffe
    -0.62
    è¦ļéĨĴ
    -0.62
    holding
    -0.60
     ash
    -0.59
     Tinker
    -0.59
     Able
    -0.59
     Barnett
    -0.59
    POSITIVE LOGITS
    terday
    1.06
    urable
    0.97
    umer
    0.91
    manship
    0.89
    ource
    0.88
    chant
    0.88
    uits
    0.87
    omed
    0.87
    ailing
    0.87
    uit
    0.86
    Activations Density 0.018%

    No Known Activations