© 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. 22133
    Prev
    Next
    INDEX
    Explanations

    statements discussing impartiality or bias

    oai_token-act-pair · gpt-3.5-turbo

    terms related to neutrality and bias in discussions or reports

    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
    Phones
    -0.78
    clamation
    -0.76
    âĹ¼
    -0.76
    Pause
    -0.75
    RAM
    -0.75
    trap
    -0.75
    Requires
    -0.74
     Extended
    -0.72
    KER
    -0.70
    FFER
    -0.69
    POSITIVE LOGITS
     impartial
    1.30
     unbiased
    1.16
     observer
    1.06
     observers
    0.92
     opinions
    0.91
     arbit
    0.89
    iate
    0.86
     opinion
    0.82
    ity
    0.80
     viewpoints
    0.79
    Activations Density 0.027%

    No Known Activations