© 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. 9-RES-JB
    11. 17963
    Prev
    Next
    INDEX
    Explanations

    names or terms related to places or people with 'Lang' in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lang."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compensated
    -0.75
    ItemTracker
    -0.70
    ÄŁ
    -0.64
    ÏĢ
    -0.63
     prosecut
    -0.62
     exclus
    -0.61
     nonex
    -0.59
     compensate
    -0.58
    ×ij
    -0.58
     listener
    -0.58
    POSITIVE LOGITS
    strom
    1.07
    gow
    1.05
    ley
    1.05
    ford
    1.05
    dale
    1.03
    enberg
    1.00
    mu
    0.98
    quist
    0.92
    ston
    0.92
    shaw
    0.90
    Activations Density 0.066%

    No Known Activations