© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 24000
    Prev
    Next
    INDEX
    Explanations

    instances of movement or change in location

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     %%
    -0.71
     NETWORK
    -0.70
     taught
    -0.68
    Voice
    -0.68
     compares
    -0.63
     debuted
    -0.62
    Trend
    -0.62
     worked
    -0.62
     summed
    -0.62
     contrasted
    -0.60
    POSITIVE LOGITS
     order
    1.14
     dro
    1.07
     lieu
    1.06
    animate
    1.02
    patient
    1.01
     vitro
    0.99
     favor
    0.98
     hopes
    0.95
    escap
    0.94
     accordance
    0.93
    Activations Density 0.301%

    No Known Activations