© 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. 11-RES-JB
    11. 6865
    Prev
    Next
    INDEX
    Explanations

    descriptions of qualities or qualifications needed in candidates or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to individuals in various contexts, especially those associated with specific roles or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.83
     concluding
    -0.76
     resulting
    -0.72
    NetMessage
    -0.63
    ummer
    -0.58
     initiation
    -0.57
     culminating
    -0.56
     awarding
    -0.56
     retreating
    -0.56
     dwindling
    -0.55
    POSITIVE LOGITS
     understands
    1.10
     specialize
    1.03
     genuinely
    1.00
     embody
    0.99
     understand
    0.97
     can
    0.94
     specializes
    0.94
     knows
    0.92
     aren
    0.90
     cares
    0.88
    Activations Density 0.177%

    No Known Activations