© 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. 8-RES-JB
    11. 8547
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "lower."

    oai_token-act-pair · gpt-3.5-turbo

    references to socioeconomic status, particularly relating to lower income levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.70
    aint
    -0.70
    Pros
    -0.70
     Outbreak
    -0.66
    NEWS
    -0.65
    ACK
    -0.65
    MO
    -0.62
    Jew
    -0.62
    OVA
    -0.62
    Reply
    -0.61
    POSITIVE LOGITS
    case
    1.07
    iating
    0.99
     than
    0.87
    iation
    0.86
     extrem
    0.85
     inhib
    0.85
     jaw
    0.81
     grades
    0.80
    down
    0.78
    iated
    0.76
    Activations Density 0.029%

    No Known Activations