Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 3250
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases with colors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to socioeconomic status distinctions, particularly focused on "blue-collar" references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dickinson
    -0.77
    ulhu
    -0.75
     Shutterstock
    -0.75
    hran
    -0.74
     Cumm
    -0.71
     Norris
    -0.70
    OTOS
    -0.67
     Rica
    -0.65
     Annotations
    -0.64
     FML
    -0.64
    POSITIVE LOGITS
    sounding
    1.18
    eyed
    1.17
    haired
    1.13
    footed
    1.12
    legged
    1.09
    faced
    1.03
    colored
    1.03
    clad
    1.02
    wing
    1.00
    headed
    1.00
    Activations Density 0.069%

    No Known Activations