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. 13732
    Prev
    Next
    INDEX
    Explanations

    words related to telecommunications, especially those starting with "tele"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to telecommunication technology

    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
     Bridgewater
    -0.73
     Cumber
    -0.72
     Stafford
    -0.72
     Hardy
    -0.71
    âĿ
    -0.70
    âĨij
    -0.68
     Heights
    -0.67
    âĺħâĺħ
    -0.67
    inventoryQuantity
    -0.66
    Reloaded
    -0.66
    POSITIVE LOGITS
    metry
    1.13
    pathic
    1.09
    ported
    1.07
     tele
    1.00
    communication
    0.99
    pathy
    0.97
    porting
    0.96
    caster
    0.95
    casters
    0.94
    porter
    0.93
    Activations Density 0.010%

    No Known Activations