© 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. 22225
    Prev
    Next
    INDEX
    Explanations

    phrases related to being hired or fired

    oai_token-act-pair · gpt-3.5-turbo

    words related to hiring and employment

    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
    eston
    -0.67
    arov
    -0.64
    ascript
    -0.63
    oulos
    -0.62
    åij
    -0.62
     Bei
    -0.61
     reconc
    -0.61
     contingency
    -0.58
    Orig
    -0.58
    ļé
    -0.58
    POSITIVE LOGITS
    lessly
    0.94
    rack
    0.85
    ired
    0.80
    wolves
    0.80
    rss
    0.76
    anto
    0.76
    sbm
    0.74
    rums
    0.73
    ansas
    0.73
    iring
    0.72
    Activations Density 0.014%

    No Known Activations