© 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. 0-RES-JB
    11. 14658
    Prev
    Next
    INDEX
    Explanations

    words related to unity and support among groups of people

    oai_token-act-pair · gpt-3.5-turbo

    themes of solidarity and support within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambling
    -0.67
     knob
    -0.67
    PG
    -0.65
     dial
    -0.65
     Tooth
    -0.64
    mith
    -0.62
    VR
    -0.62
    irs
    -0.61
    Ob
    -0.60
    ook
    -0.60
    POSITIVE LOGITS
     solidarity
    3.73
     sympathy
    1.64
     unity
    1.49
     empathy
    1.30
     gratitude
    1.27
     cooperation
    1.25
     patriotism
    1.18
     generosity
    1.17
     activism
    1.16
     cohesion
    1.13
    Activations Density 0.013%

    No Known Activations