© 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. 10-RES-JB
    11. 1437
    Prev
    Next
    INDEX
    Explanations

    references to political affiliations and positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political parties and candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.81
    acci
    -0.78
    icum
    -0.78
    phasis
    -0.77
    iphate
    -0.77
    imaru
    -0.74
    Downloadha
    -0.73
    ailable
    -0.69
    peak
    -0.68
    abiding
    -0.67
    POSITIVE LOGITS
     newcomer
    1.25
     writer
    1.24
     filmmaker
    1.23
     guru
    1.20
     blogger
    1.15
     columnist
    1.15
     novelist
    1.14
     entrepreneur
    1.14
     superstar
    1.14
     comedian
    1.14
    Activations Density 0.395%

    No Known Activations