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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11366
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or information exchange between different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to methodologies or processes involving representation or communication

    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
    emort
    -0.71
    terday
    -0.69
     worshipped
    -0.66
    ãĤº
    -0.66
    anooga
    -0.65
    nai
    -0.64
    hesda
    -0.62
    olor
    -0.62
     Zup
    -0.60
    anke
    -0.59
    POSITIVE LOGITS
     prism
    1.18
     channels
    1.17
     intermediary
    1.14
     lens
    1.03
     intermedi
    1.00
     mechanisms
    0.92
     backdoor
    0.85
     conduit
    0.84
     mediation
    0.84
     tunnels
    0.82
    Activations Density 0.262%

    No Known Activations