© 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. 0-RES-JB
    11. 5057
    Prev
    Next
    INDEX
    Explanations

    words related to hiring or employment

    oai_token-act-pair · gpt-3.5-turbo

    references to retirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scales
    -0.66
     scale
    -0.65
     crystal
    -0.62
     shards
    -0.61
     strat
    -0.60
     proportions
    -0.59
     amplification
    -0.59
     smack
    -0.59
     mobility
    -0.59
     Crystal
    -0.58
    POSITIVE LOGITS
    ired
    4.54
    IRED
    2.66
    iring
    2.53
    ires
    2.30
    irable
    1.89
    ire
    1.86
    irement
    1.70
    iration
    1.42
    irements
    1.34
    isition
    1.34
    Activations Density 0.012%

    No Known Activations