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. 1-RES-JB
    6. 9837
    Prev
    Next
    INDEX
    Explanations

    words related to technology and devices, particularly with a focus on "te" in the activation values

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "te" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     timelines
    -0.66
     eleph
    -0.65
    espie
    -0.64
     margins
    -0.63
     caps
    -0.63
     fronts
    -0.62
     FISA
    -0.62
     flaw
    -0.62
     SHALL
    -0.62
     containment
    -0.59
    POSITIVE LOGITS
    brate
    1.30
    brates
    1.21
    ppo
    1.19
    te
    1.16
    achers
    1.15
    eca
    1.12
    levision
    1.10
    llers
    1.07
    ller
    1.05
    acher
    0.99
    Activations Density 0.012%

    No Known Activations