© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    words related to expressing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional response, particularly regarding lamentation and the quality of people or situations

    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
    cius
    -0.76
     custody
    -0.61
     advisers
    -0.57
    BOOK
    -0.57
     Madison
    -0.57
    mberg
    -0.56
     conservatives
    -0.56
     Angels
    -0.56
     Lumpur
    -0.55
    âĺħâĺħ
    -0.55
    POSITIVE LOGITS
    ally
    1.51
    ality
    1.28
    nel
    1.27
    ation
    1.25
    ations
    1.20
    ional
    1.19
    alities
    1.18
    naire
    1.13
    ately
    1.13
    als
    1.09
    Activations Density 0.043%

    No Known Activations