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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4074
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    references to complaints and grievances

    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
    unin
    -0.73
     Kop
    -0.69
     alive
    -0.65
    chie
    -0.64
    rican
    -0.63
    Alpha
    -0.63
     Sagan
    -0.62
     Sequence
    -0.62
    olit
    -0.61
     Recon
    -0.61
    POSITIVE LOGITS
     complaints
    3.61
     complaint
    2.59
     grievances
    2.16
     complain
    2.09
     complains
    2.05
     criticisms
    1.90
     objections
    1.88
     accusations
    1.78
     complained
    1.72
     complaining
    1.68
    Activations Density 0.016%

    No Known Activations