© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6657
    Prev
    Next
    INDEX
    Explanations

    verb forms such as past tense, present perfect tense, and future tense

    oai_token-act-pair · gpt-3.5-turbo

    key terms associated with contracts and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pop
    -0.80
    Posts
    -0.76
    population
    -0.75
    ugen
    -0.75
    sylv
    -0.74
    roller
    -0.72
    ogging
    -0.71
    perture
    -0.71
    rehens
    -0.71
    ensity
    -0.70
    POSITIVE LOGITS
     agreements
    2.08
     agreement
    2.02
     deal
    1.91
     contracts
    1.87
     contract
    1.86
     pact
    1.83
     deals
    1.80
     negotiated
    1.63
     Agreement
    1.63
     negotiations
    1.61
    Activations Density 0.565%

    No Known Activations