© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 5629
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'fair' used in a context related to justice, equality, or fairness

    oai_token-act-pair · gpt-3.5-turbo

    references to fairness and equitable treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apse
    -0.82
    CHAT
    -0.79
    uality
    -0.75
    Ultra
    -0.66
    clips
    -0.65
     Reincarnated
    -0.63
    hent
    -0.63
    cano
    -0.63
    OUS
    -0.61
    Extra
    -0.60
    POSITIVE LOGITS
    grounds
    1.26
    yt
    1.16
    ground
    0.91
    fair
    0.87
    iciary
    0.85
     fair
    0.84
    child
    0.79
    abouts
    0.78
    fare
    0.75
    ies
    0.74
    Activations Density 0.017%

    No Known Activations