© 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. 18209
    Prev
    Next
    INDEX
    Explanations

    instances where something is prevented or hindered by certain restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "due" indicating causation or reasons for situations

    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
    =-=-=-=-=-=-=-=-
    -0.63
     Phant
    -0.57
    oola
    -0.54
    adel
    -0.52
    oos
    -0.52
     Confederation
    -0.51
    nova
    -0.51
    aden
    -0.51
    affe
    -0.50
    dar
    -0.50
    POSITIVE LOGITS
     diligence
    1.04
     to
    1.00
    lling
    0.82
     largely
    0.80
     mainly
    0.78
     solely
    0.78
     thereto
    0.77
     primarily
    0.74
    itiz
    0.72
    llers
    0.71
    Activations Density 0.026%

    No Known Activations