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. 9-RES-JB
    6. 11000
    Prev
    Next
    INDEX
    Explanations

    words related to valuable and precious items

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of value and preciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.78
    abad
    -0.76
    zai
    -0.75
    Nap
    -0.75
    LINE
    -0.72
    alis
    -0.70
    yeah
    -0.69
     pronounced
    -0.69
    imposed
    -0.68
    named
    -0.67
    POSITIVE LOGITS
     possessions
    1.13
     asset
    1.02
    itton
    0.94
     valuable
    0.92
     metals
    0.91
     resources
    0.91
     belongings
    0.90
     commodity
    0.88
     resource
    0.85
     assets
    0.82
    Activations Density 0.044%

    No Known Activations