© 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. 6-RES-JB
    6. 20608
    Prev
    Next
    INDEX
    Explanations

    words related to the idea of continuation or persistence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continued" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARP
    -0.79
    IDS
    -0.79
    flix
    -0.76
    ridges
    -0.76
    wright
    -0.75
    bridge
    -0.75
    rette
    -0.74
     Tycoon
    -0.74
    ISTER
    -0.73
    tag
    -0.72
    POSITIVE LOGITS
     existence
    1.10
     possession
    0.93
     occurrences
    0.92
     absence
    0.90
     attempts
    0.90
     consideration
    0.89
     occurrence
    0.88
     effort
    0.88
     employment
    0.87
     efforts
    0.87
    Activations Density 0.046%

    No Known Activations