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. 23330
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "sil"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "silence" or its variations in context

    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
     Blessed
    -0.64
     damned
    -0.63
     quarters
    -0.63
    OTAL
    -0.63
     Emmanuel
    -0.62
     ranking
    -0.61
    ELS
    -0.60
     Pose
    -0.59
     Das
    -0.58
     RAD
    -0.58
    POSITIVE LOGITS
    encing
    1.60
    encer
    1.57
    encers
    1.55
    enced
    1.46
    ences
    1.43
    icone
    1.28
    icon
    1.14
    hou
    1.14
    ken
    1.12
    ence
    1.12
    Activations Density 0.028%

    No Known Activations