© 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. 10-RES-JB
    11. 13976
    Prev
    Next
    INDEX
    Explanations

    people's actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" in various contexts, often referring to individuals or groups involved in actions or situations

    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
     Delicious
    -0.65
    OUND
    -0.64
    ogue
    -0.63
     Connection
    -0.62
     srfAttach
    -0.61
     Decay
    -0.61
     Bound
    -0.59
    UGE
    -0.59
    PORT
    -0.59
    ranging
    -0.58
    POSITIVE LOGITS
     knows
    1.45
     thinks
    1.40
     loves
    1.40
     understands
    1.38
     cares
    1.37
     hates
    1.35
     wants
    1.35
     wears
    1.33
     prefers
    1.30
     enjoys
    1.30
    Activations Density 0.124%

    No Known Activations