© 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. 6148
    Prev
    Next
    INDEX
    Explanations

    words related to being unpopular or disapproved

    oai_token-act-pair · gpt-3.5-turbo

    references to unpopularity

    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
    chn
    -0.81
    urers
    -0.79
    ramid
    -0.77
    ural
    -0.77
    tein
    -0.73
    dress
    -0.73
    ynthesis
    -0.71
    phasis
    -0.69
    AUT
    -0.69
    á
    -0.68
    POSITIVE LOGITS
     unpopular
    1.33
    ity
    1.16
     incumbent
    0.93
    ities
    0.86
     disadvant
    0.78
     burdens
    0.77
     taboo
    0.77
     sidel
    0.74
    liest
    0.72
     compromises
    0.72
    Activations Density 0.008%

    No Known Activations