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. 470
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of alignment or correspondence between different entities or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reflect" and its variations, indicating a focus on the concept of reflection or representation in various contexts

    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
    ciating
    -0.83
    anch
    -0.81
    kees
    -0.72
     externalToEVAOnly
    -0.70
    queue
    -0.69
     Unloaded
    -0.68
    sites
    -0.68
    ccess
    -0.67
    weed
    -0.65
    efer
    -0.65
    POSITIVE LOGITS
    ively
    0.95
     reflected
    0.84
     sunlight
    0.83
     reflections
    0.80
    iveness
    0.77
    orical
    0.71
     reflect
    0.70
     reflection
    0.70
     opin
    0.69
    iments
    0.68
    Activations Density 0.034%

    No Known Activations