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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 7108
    Prev
    Next
    INDEX
    Explanations

    words related to the term "raz", possibly referring to a specific concept or entity

    oai_token-act-pair · gpt-3.5-turbo

    the term "raz" and related administrative or protocol references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STAR
    -0.67
     Isles
    -0.66
     gem
    -0.65
     rope
    -0.64
    woods
    -0.61
     Mahar
    -0.61
     steep
    -0.60
     Pebble
    -0.60
     stump
    -0.60
     fitt
    -0.59
    POSITIVE LOGITS
    edly
    1.14
    ed
    1.05
    es
    1.02
    xual
    1.01
    ured
    0.96
    orial
    0.96
    urer
    0.94
    ese
    0.93
    er
    0.91
    ation
    0.90
    Activations Density 0.072%

    No Known Activations