© 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 EvalsExportsinterp-engineNEWAPI 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. 16666
    Prev
    Next
    INDEX
    Explanations

    words related to a downward trend or decrease

    oai_token-act-pair · gpt-3.5-turbo

    terms indicative of negative trends or declines

    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
    aque
    -0.83
    andise
    -0.82
    ayn
    -0.77
    ortment
    -0.77
    aques
    -0.77
    anooga
    -0.76
    onomic
    -0.75
    orthy
    -0.75
    hetti
    -0.75
    aqu
    -0.74
    POSITIVE LOGITS
     spiral
    1.02
     plummet
    0.76
     inhib
    0.76
     depress
    0.74
     declining
    0.73
     spir
    0.73
     Dwell
    0.72
    «ĺ
    0.71
     plag
    0.69
     Blues
    0.69
    Activations Density 0.022%

    No Known Activations