© 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. 9-RES-JB
    11. 15638
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "half" and a subsequent number indicating a specific fraction or amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "half-time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clash
    -0.70
     QC
    -0.69
     Conquer
    -0.68
     escalation
    -0.66
     nexus
    -0.65
     dictate
    -0.64
     services
    -0.64
    eers
    -0.64
     Cassidy
    -0.63
     Ink
    -0.62
    POSITIVE LOGITS
    dozen
    1.46
    assed
    1.31
    century
    1.19
    hour
    1.18
    hearted
    1.18
    heartedly
    1.18
    empty
    1.12
    moon
    1.05
    inch
    1.05
    finished
    1.03
    Activations Density 0.032%

    No Known Activations