© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    words related to disadvantages or negative aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to disadvantages in various contexts

    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
     Thumbnails
    -0.71
    phony
    -0.69
     ðŁ
    -0.68
    pol
    -0.66
    apps
    -0.63
    prints
    -0.63
     translations
    -0.63
     answers
    -0.62
    ream
    -0.61
    ews
    -0.61
    POSITIVE LOGITS
     disadvantage
    4.17
     disadvantages
    2.78
    advant
    1.97
     disadvant
    1.92
     drawback
    1.86
     detriment
    1.85
     downside
    1.75
     advantage
    1.64
     disadvantaged
    1.58
     advant
    1.57
    Activations Density 0.014%

    No Known Activations