© 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. 4-RES-JB
    11. 22603
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions or sentiments related to the heart

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "heart," often in emotional or metaphorical contexts

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

    No Comments

    Negative Logits
     Motorsport
    -0.74
     newsp
    -0.72
    VICE
    -0.72
     Cheong
    -0.66
     Lavrov
    -0.66
    USS
    -0.65
     Sigma
    -0.63
     Sessions
    -0.63
    dq
    -0.63
     Vehicles
    -0.63
    POSITIVE LOGITS
    strings
    1.10
    rend
    0.98
    warming
    0.94
    ily
    0.92
    lake
    0.92
    heart
    0.91
    beat
    0.90
    burn
    0.88
     heart
    0.84
    broken
    0.84
    Activations Density 0.018%

    No Known Activations