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. 3-RES-JB
    6. 7795
    Prev
    Next
    INDEX
    Explanations

    phrases related to durability and resistant materials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to durability and strength of materials or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cedented
    -0.86
    peak
    -0.85
    OPA
    -0.83
    utra
    -0.83
    olitan
    -0.80
    atri
    -0.77
    ffic
    -0.77
    onia
    -0.74
    hra
    -0.73
    corn
    -0.73
    POSITIVE LOGITS
     durability
    1.01
     durable
    0.93
     adhesive
    0.82
     armour
    0.82
     fabrics
    0.82
     glue
    0.81
     fabric
    0.80
     plastics
    0.80
     goods
    0.78
     sturdy
    0.77
    Activations Density 0.036%

    No Known Activations