© 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. 6931
    Prev
    Next
    INDEX
    Explanations

    words related to negative trends or decreases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decline."

    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
    tein
    -0.72
    Sources
    -0.66
     Stadium
    -0.65
    ":[{"
    -0.63
    iliary
    -0.61
    Offline
    -0.61
    neys
    -0.61
    ships
    -0.61
     Helpful
    -0.59
    enfranch
    -0.58
    POSITIVE LOGITS
     decline
    0.88
     declines
    0.85
     attrition
    0.77
     escal
    0.74
    ylon
    0.73
     precip
    0.71
     reduction
    0.71
     slump
    0.71
    ous
    0.70
     degradation
    0.69
    Activations Density 0.020%

    No Known Activations