© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3802
    Prev
    Next
    INDEX
    Explanations

    instances where something was created, discovered, invented, or first developed

    oai_token-act-pair · gpt-3.5-turbo

    historical references and events

    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
    oodle
    -0.66
    ouf
    -0.64
    affle
    -0.63
    blogs
    -0.63
     GoPro
    -0.62
     )))
    -0.62
     Repeat
    -0.60
    ophe
    -0.57
    asma
    -0.57
     hasht
    -0.57
    POSITIVE LOGITS
     circa
    1.28
     centuries
    1.24
     1870
    1.22
     1895
    1.22
     1910
    1.21
     1897
    1.21
     1935
    1.20
     1890
    1.20
     1896
    1.19
     1888
    1.18
    Activations Density 0.373%

    No Known Activations