© 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. 3-RES-JB
    11. 24323
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative impacts or disadvantages

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate negative consequences or inferior status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bio
    -0.66
    CHA
    -0.60
    oother
    -0.60
    âķIJâķIJ
    -0.60
    Fit
    -0.58
    ================
    -0.58
     Synt
    -0.58
    rue
    -0.58
     harness
    -0.57
    maximum
    -0.57
    POSITIVE LOGITS
    pora
    0.83
    itized
    0.82
     disadvant
    0.82
    pret
    0.78
    nces
    0.76
     detriment
    0.75
     releg
    0.75
    xual
    0.75
    ietal
    0.74
    ovan
    0.71
    Activations Density 0.024%

    No Known Activations