© 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. 2-RES-JB
    11. 5263
    Prev
    Next
    INDEX
    Explanations

    words related to potential or expected outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to future outcomes or predictions

    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
    HOU
    -0.76
    tick
    -0.73
    ku
    -0.72
    lua
    -0.71
    PAC
    -0.69
    gas
    -0.69
    raph
    -0.68
    kef
    -0.68
    kar
    -0.67
    emen
    -0.66
    POSITIVE LOGITS
    ities
    0.98
     demise
    0.94
    ity
    0.93
     downfall
    0.92
     eventual
    0.89
     embodiments
    0.85
     legalization
    0.81
     vict
    0.81
     abolition
    0.78
     winner
    0.77
    Activations Density 0.005%

    No Known Activations