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. 10-RES-JB
    6. 2405
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes or performance characteristics with a focus on specifics like material, load capacity, strength, or effectiveness

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical durability and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entitlement
    -0.72
     subscrib
    -0.71
    creator
    -0.65
     Registrar
    -0.64
    otide
    -0.62
    orate
    -0.62
     anew
    -0.62
    endant
    -0.61
    oday
    -0.61
     entit
    -0.61
    POSITIVE LOGITS
     daylight
    1.06
     indoors
    1.03
     outdoors
    1.01
     temperatures
    1.01
     colder
    0.99
     climates
    0.97
     environments
    0.96
     hars
    0.95
     daytime
    0.94
     prolonged
    0.91
    Activations Density 0.348%

    No Known Activations