© 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. 6-RES-JB
    11. 2627
    Prev
    Next
    INDEX
    Explanations

    words related to technology and internet domains

    oai_token-act-pair · gpt-3.5-turbo

    the word "as."

    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
     thumbnail
    -0.76
    OUGH
    -0.75
    LINE
    -0.67
    ship
    -0.67
    ARGET
    -0.67
    OWS
    -0.61
    SOURCE
    -0.60
    Submit
    -0.60
    sheet
    -0.59
     MFT
    -0.59
    POSITIVE LOGITS
    aurus
    1.26
    ylum
    1.13
    ync
    1.12
    quez
    1.10
    pect
    1.08
    leep
    1.06
    hens
    1.05
    peed
    1.05
    utra
    1.04
    pell
    1.04
    Activations Density 0.035%

    No Known Activations