Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10128
    Prev
    Next
    INDEX
    Explanations

    words related to negative or harmful cycles and struggles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cycles of negative social or economic conditions

    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
    osponsors
    -0.94
    ints
    -0.93
    notes
    -0.88
    parts
    -0.86
     Shares
    -0.82
    stones
    -0.82
    Points
    -0.80
    DERR
    -0.78
    keys
    -0.78
    points
    -0.78
    POSITIVE LOGITS
     epidemic
    1.34
     onslaught
    1.25
     tide
    1.23
     crusade
    1.22
     cycle
    1.18
     insurgency
    1.17
     phenomenon
    1.16
     frenzy
    1.14
     trend
    1.13
     vortex
    1.11
    Activations Density 0.287%

    No Known Activations