© 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. 22854
    Prev
    Next
    INDEX
    Explanations

    passages referring to the concept of a process

    oai_token-act-pair · gpt-3.5-turbo

    references to a "process."

    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
    acious
    -0.80
    Sport
    -0.74
    orthy
    -0.70
    acea
    -0.69
    kernel
    -0.68
    ledged
    -0.68
    bors
    -0.68
    worthy
    -0.68
    fml
    -0.67
    acies
    -0.67
    POSITIVE LOGITS
     extracting
    1.12
     selecting
    1.12
     constructing
    1.11
     acquiring
    1.10
     electing
    1.10
     obtaining
    1.09
     transferring
    1.09
     converting
    1.08
     separating
    1.06
     assembling
    1.05
    Activations Density 0.100%

    No Known Activations