© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6832
    Prev
    Next
    INDEX
    Explanations

    interview-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interview."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cil
    -0.75
    axy
    -0.74
    ¶ħ
    -0.74
    ricanes
    -0.71
    math
    -0.71
    cream
    -0.70
    sels
    -0.70
    hover
    -0.69
    ple
    -0.69
    little
    -0.68
    POSITIVE LOGITS
     interview
    1.14
     interviews
    1.10
     Interview
    0.94
     Transcript
    0.91
    Interview
    0.86
    ees
    0.86
     transcripts
    0.82
     interviewing
    0.82
     interviewer
    0.82
    ysis
    0.78
    Activations Density 0.017%

    No Known Activations