© 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. 7-RES-JB
    11. 2211
    Prev
    Next
    INDEX
    Explanations

    phrases related to standing out positively or being exceptional

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shine" and its variations, indicating a focus on themes of illumination or prominence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essor
    -0.77
    agara
    -0.71
    ilage
    -0.70
    artment
    -0.69
    assian
    -0.68
    went
    -0.68
    urally
    -0.67
    tarian
    -0.65
    rieg
    -0.65
    apist
    -0.65
    POSITIVE LOGITS
     shone
    1.16
     brightly
    1.08
     brighter
    1.08
     shines
    1.06
     shine
    1.06
     brightest
    1.03
    lights
    0.93
     shining
    0.90
     headlights
    0.85
    elight
    0.83
    Activations Density 0.048%

    No Known Activations