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. 2-RES-JB
    6. 7521
    Prev
    Next
    INDEX
    Explanations

    phrases related to job positions or levels, particularly focusing on the concept of "entry level."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "entry" related to various contexts, particularly in job or access scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carth
    -0.72
     opio
    -0.71
    velength
    -0.69
    =-=-=-=-=-=-=-=-
    -0.67
     tremend
    -0.66
    acca
    -0.64
    rica
    -0.63
     Balanced
    -0.62
     Estate
    -0.62
    illac
    -0.62
    POSITIVE LOGITS
     entry
    1.04
     Entry
    0.94
     entries
    0.86
    breakers
    0.78
    entry
    0.74
     clearance
    0.74
    Entry
    0.73
    door
    0.71
    prises
    0.71
    prise
    0.69
    Activations Density 0.012%

    No Known Activations