© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7215
    Prev
    Next
    INDEX
    Explanations

    parallels and analogies between different subjects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comparisons and similarities

    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
    Interstitial
    -0.77
    rieve
    -0.70
    Ķ
    -0.68
    Assembly
    -0.68
    Asset
    -0.68
    Published
    -0.67
    spe
    -0.67
    absor
    -0.67
    Drag
    -0.67
    -+-+-+-+
    -0.65
    POSITIVE LOGITS
     parallels
    1.24
     similarities
    0.94
     comparisons
    0.93
    isons
    0.78
     twins
    0.76
    lihood
    0.76
     linking
    0.74
     tracing
    0.71
    xual
    0.71
     echoes
    0.71
    Activations Density 0.013%

    No Known Activations