© 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. 10-RES-JB
    11. 6736
    Prev
    Next
    INDEX
    Explanations

    discussions or scenarios where individuals or groups come to a shared understanding or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come to the" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}}
    -0.86
    TION
    -0.85
    rand
    -0.73
    vich
    -0.72
    taboola
    -0.67
    tim
    -0.66
    verson
    -0.65
    naire
    -0.62
    inventoryQuantity
    -0.62
    jay
    -0.61
    POSITIVE LOGITS
     forefront
    1.39
     conclusion
    1.21
     table
    1.16
     rescue
    1.12
     realization
    1.09
     doorstep
    1.07
     shores
    1.07
     fray
    1.05
     attention
    1.03
     fold
    0.94
    Activations Density 0.132%

    No Known Activations