© 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. 3-RES-JB
    11. 1889
    Prev
    Next
    INDEX
    Explanations

    references to the ability of individuals or entities to perform certain actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to "ability" or capabilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cortex
    -0.67
     Traffic
    -0.66
     Benz
    -0.65
     1944
    -0.65
     Matter
    -0.65
     1941
    -0.65
     Oak
    -0.64
     1895
    -0.64
     Seas
    -0.64
     1943
    -0.64
    POSITIVE LOGITS
    auga
    1.05
    anooga
    0.96
    ibilities
    0.95
    Ability
    0.95
    reys
    0.93
     ability
    0.92
    ibility
    0.90
    awaru
    0.89
    yip
    0.84
    Reviewer
    0.84
    Activations Density 0.026%

    No Known Activations