© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 9541
    Prev
    Next
    INDEX
    Explanations

    words related to compassion or passionate actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "compassion" and related forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clojure
    -0.69
     NX
    -0.64
     MacDonald
    -0.64
    SM
    -0.63
     IGF
    -0.63
     mesh
    -0.62
     deviation
    -0.62
     systems
    -0.61
     Nordic
    -0.60
     deviations
    -0.60
    POSITIVE LOGITS
    assion
    1.24
    ality
    1.04
    ally
    1.03
    nel
    1.03
    naire
    1.02
    aly
    1.01
    icion
    0.96
    ate
    0.95
    alist
    0.94
    edIn
    0.91
    Activations Density 0.022%

    No Known Activations