© 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. 10302
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of people being interviewed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interviewed."

    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
     sac
    -0.65
     supremacy
    -0.63
     ease
    -0.63
    ense
    -0.62
     destiny
    -0.62
     resolve
    -0.61
     precedence
    -0.61
    livion
    -0.60
     usage
    -0.60
     potent
    -0.59
    POSITIVE LOGITS
     interviewed
    3.66
     interviewing
    2.25
     interviews
    1.96
     interview
    1.81
     Interview
    1.75
     surveyed
    1.71
    Interview
    1.70
     interrogated
    1.65
     interviewer
    1.64
     contacted
    1.57
    Activations Density 0.013%

    No Known Activations