© 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. 10-RES-JB
    11. 23211
    Prev
    Next
    INDEX
    Explanations

    phrases with the structure "in the *"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -0.86
    naissance
    -0.75
    olicy
    -0.75
    PsyNetMessage
    -0.74
    SPONSORED
    -0.71
    iliary
    -0.69
    Ç
    -0.69
    nces
    -0.67
    nesday
    -0.67
    LEASE
    -0.66
    POSITIVE LOGITS
     midst
    1.01
     drawer
    0.95
     closet
    0.95
     oven
    0.91
     weeds
    0.88
     trenches
    0.88
    aters
    0.87
     towel
    0.86
     pudding
    0.86
     hole
    0.85
    Activations Density 0.107%

    No Known Activations