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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-RES-JB
    6. 40
    Prev
    Next
    INDEX
    Explanations

    combinations of different elements or factors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combination."

    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
     ¶
    -0.73
    asks
    -0.69
    yrights
    -0.67
    peak
    -0.65
    orns
    -0.64
    thood
    -0.63
    Ship
    -0.62
    ÃŃ
    -0.61
    İ
    -0.60
    rift
    -0.60
    POSITIVE LOGITS
     combination
    4.01
     combinations
    2.51
     mixture
    2.07
     combo
    1.90
     conjunction
    1.75
     blend
    1.64
     mix
    1.58
     combined
    1.55
     tandem
    1.55
     combine
    1.35
    Activations Density 0.011%

    No Known Activations