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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 5088
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the durability or resistance of materials or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to durability and sturdiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.89
    ffic
    -0.81
    athetic
    -0.77
    olic
    -0.77
    corn
    -0.74
    cedented
    -0.73
    onia
    -0.71
    olitan
    -0.67
    bara
    -0.67
    via
    -0.66
    POSITIVE LOGITS
     durability
    1.08
     durable
    1.00
     resilience
    0.84
     glue
    0.79
     armour
    0.78
     fabric
    0.78
     sturdy
    0.77
     adhesive
    0.75
     resilient
    0.75
     fabrics
    0.74
    Activations Density 0.022%

    No Known Activations