© 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 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. 10-RES-JB
    11. 6062
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases describing significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "an", indicating a focus on nonspecific entities or concepts

    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
    ventures
    -0.63
    birds
    -0.61
     Prompt
    -0.61
     Talks
    -0.61
    kai
    -0.60
     Regions
    -0.60
    root
    -0.60
    licks
    -0.59
    âĸº
    -0.59
    bots
    -0.58
    POSITIVE LOGITS
    ointed
    1.14
     indication
    1.14
     integral
    1.12
     anomaly
    1.10
     impossibility
    1.06
    omaly
    1.06
     enormous
    1.05
     invitation
    1.04
     uphill
    1.03
     understatement
    1.03
    Activations Density 0.130%

    No Known Activations