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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22602
    Prev
    Next
    INDEX
    Explanations

    terms related to aspirations or imagined scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases and sentiments related to dreams and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.82
    ento
    -0.81
    note
    -0.72
    gap
    -0.72
    abus
    -0.72
     matter
    -0.67
    Side
    -0.67
    inventoryQuantity
    -0.66
    issue
    -0.66
     matters
    -0.66
    POSITIVE LOGITS
     someday
    1.34
     immortality
    1.00
     greatness
    0.86
     redemption
    0.83
     emulate
    0.82
    thood
    0.81
     perfection
    0.81
     paradise
    0.80
     limitless
    0.79
     utopian
    0.79
    Activations Density 0.225%

    No Known Activations