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. 0-RES-JB
    6. 3139
    Prev
    Next
    INDEX
    Explanations

    technology-related terms or references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word 'Tech' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     begg
    -0.69
     association
    -0.68
     bare
    -0.68
     bargaining
    -0.68
     partition
    -0.67
    mble
    -0.67
     cardinal
    -0.66
     pane
    -0.66
     cottage
    -0.65
     autobi
    -0.65
    POSITIVE LOGITS
    Tech
    4.04
     Tech
    2.44
    tech
    2.03
     tech
    1.72
    Technology
    1.64
     Technology
    1.46
    otech
    1.37
     TECH
    1.36
     Technologies
    1.34
    technology
    1.27
    Activations Density 0.019%

    No Known Activations