© 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. 10-RES-JB
    11. 1410
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes in job roles and organizational positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of personnel changes and replacements in an organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abiding
    -0.83
     corrid
    -0.82
     spectators
    -0.78
     sinners
    -0.77
     tourists
    -0.76
     smugglers
    -0.75
     postage
    -0.73
     robbers
    -0.70
     crucifix
    -0.70
     outlaw
    -0.69
    POSITIVE LOGITS
     resigned
    1.35
     resign
    1.32
     overseeing
    1.24
     resignation
    1.18
     duties
    1.16
     appointed
    1.13
     appoint
    1.13
     oversee
    1.13
     replaces
    1.11
     oversaw
    1.11
    Activations Density 0.648%

    No Known Activations