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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3202
    Prev
    Next
    INDEX
    Explanations

    words related to scarcity and abundance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resource scarcity and abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itect
    -0.82
    grand
    -0.73
     Enhancement
    -0.68
     Forward
    -0.66
     Orche
    -0.66
    hent
    -0.66
     Axis
    -0.65
    intention
    -0.64
    aughs
    -0.63
     Debug
    -0.62
    POSITIVE LOGITS
     scarce
    3.69
     plentiful
    2.45
     abundant
    2.04
     scarcity
    1.84
     scant
    1.80
     sparse
    1.63
     abound
    1.48
     dwindling
    1.47
     plent
    1.42
     meager
    1.37
    Activations Density 0.040%

    No Known Activations