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. 9-RES-JB
    6. 20581
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale concepts or events

    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
     Minerva
    -0.66
     Congo
    -0.65
     Keeper
    -0.64
     Cortana
    -0.64
     Cambodia
    -0.63
     Catalyst
    -0.62
     Yel
    -0.62
     Shutterstock
    -0.62
     Fidel
    -0.62
     Queens
    -0.62
    POSITIVE LOGITS
    scale
    1.45
    bodied
    1.39
    sized
    1.19
    enough
    1.17
    sounding
    1.12
    capacity
    1.10
    eyed
    1.08
    dollar
    1.05
    sided
    1.05
    budget
    1.01
    Activations Density 0.062%

    No Known Activations