© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 2040
    Prev
    Next
    INDEX
    Explanations

    references to precious stones

    oai_token-act-pair · gpt-3.5-turbo

    references to gemstones or metaphorical uses of "gems."

    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
     Parties
    -0.66
    foreseen
    -0.66
     Prob
    -0.63
    Reply
    -0.63
    olution
    -0.62
     Grounds
    -0.62
    ŃĶ
    -0.62
     Pace
    -0.62
    etheless
    -0.61
     Continued
    -0.61
    POSITIVE LOGITS
    stones
    1.42
     gems
    1.27
    stone
    1.19
     gem
    1.17
     jewels
    0.86
    gem
    0.80
    asper
    0.78
    cit
    0.78
    ãĥ£
    0.78
    ulously
    0.77
    Activations Density 0.009%

    No Known Activations