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. 6-RES-JB
    6. 6960
    Prev
    Next
    INDEX
    Explanations

    phrases related to precious things or items

    oai_token-act-pair · gpt-3.5-turbo

    the word "precious" and its variations

    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
    UP
    -0.78
     Hust
    -0.76
    NF
    -0.73
    ammers
    -0.72
    IDER
    -0.71
    REDACTED
    -0.70
    WP
    -0.69
    oker
    -0.67
    Nap
    -0.66
    ATT
    -0.66
    POSITIVE LOGITS
     metals
    1.12
     precious
    0.96
    tery
    0.83
    ldom
    0.82
    ness
    0.81
    stone
    0.77
     arte
    0.76
     stones
    0.76
     trove
    0.76
     treasures
    0.75
    Activations Density 0.016%

    No Known Activations