© 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. 6-RES-JB
    11. 19604
    Prev
    Next
    INDEX
    Explanations

    words related to actions or activities that involve movement or change

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REF
    -0.83
    eers
    -0.72
    ILLE
    -0.65
    Balance
    -0.62
    SOURCE
    -0.60
     UE
    -0.60
    inately
    -0.60
     charism
    -0.60
    AMI
    -0.58
    Variable
    -0.58
    POSITIVE LOGITS
    pace
    1.43
    paces
    1.35
    creen
    1.33
    hift
    1.32
    peed
    1.29
    heet
    1.23
    hops
    1.21
    ystem
    1.13
    mith
    1.12
    cale
    1.11
    Activations Density 0.416%

    No Known Activations