© 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. 2161
    Prev
    Next
    INDEX
    Explanations

    celebrates a sensory experience or design aspect that is exceptionally well-executed

    oai_token-act-pair · gpt-3.5-turbo

    affirmations of quality and effectiveness in various contexts

    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
     Costs
    -0.87
    iatus
    -0.81
    enary
    -0.69
    inventoryQuantity
    -0.68
    andel
    -0.68
     Shares
    -0.67
     swall
    -0.66
    azine
    -0.65
    inx
    -0.65
    whe
    -0.65
    POSITIVE LOGITS
     impecc
    1.19
     phenomenal
    1.07
     reminiscent
    1.05
     superb
    1.04
     flawless
    1.04
     markedly
    1.03
     fantastic
    1.02
     varied
    1.02
     exemplary
    1.00
     crisp
    1.00
    Activations Density 0.203%

    No Known Activations