© 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. 9-RES-JB
    11. 5928
    Prev
    Next
    INDEX
    Explanations

    similes comparing actions or situations to the behavior of something else

    oai_token-act-pair · gpt-3.5-turbo

    similes and analogies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inas
    -0.77
    ilic
    -0.73
    inion
    -0.72
    iets
    -0.72
    elin
    -0.67
    arcity
    -0.67
    nir
    -0.67
    elight
    -0.66
    ittal
    -0.65
    gence
    -0.65
    POSITIVE LOGITS
     wildfire
    1.09
    lier
    1.00
    lihood
    0.99
    liest
    0.98
     crazy
    0.98
     clock
    0.93
    minded
    0.83
     minded
    0.76
     mushrooms
    0.76
    liness
    0.75
    Activations Density 0.063%

    No Known Activations