© 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. 2-RES-JB
    11. 12626
    Prev
    Next
    INDEX
    Explanations

    instances where human abilities or skills are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "ability" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Traffic
    -0.71
    lake
    -0.70
     Oak
    -0.68
     Matter
    -0.66
     Naval
    -0.66
     Cortex
    -0.65
     Surv
    -0.64
     Camel
    -0.64
     Observ
    -0.63
     Parad
    -0.63
    POSITIVE LOGITS
     ability
    1.02
    auga
    0.99
    Ability
    0.99
    anooga
    0.88
    ibility
    0.84
    ibilities
    0.82
     impaired
    0.81
     incap
    0.80
     reperto
    0.80
    iculty
    0.79
    Activations Density 0.023%

    No Known Activations