© 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. 9-RES-JB
    11. 15651
    Prev
    Next
    INDEX
    Explanations

    descriptions of natural phenomena and geological processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to natural processes and geological formations

    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
    onomy
    -0.96
    IQ
    -0.92
    itles
    -0.82
    chart
    -0.81
    oway
    -0.81
    æĪ¦
    -0.80
    uity
    -0.80
    iland
    -0.79
     Score
    -0.78
    worth
    -0.77
    POSITIVE LOGITS
     combustion
    1.47
     collisions
    1.18
     eruption
    1.12
     volcanic
    1.12
     bombardment
    1.11
     explosions
    1.11
     drilling
    1.09
     earthquakes
    1.09
     volcan
    1.08
     gases
    1.07
    Activations Density 0.413%

    No Known Activations