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. 5-RES-JB
    6. 21522
    Prev
    Next
    INDEX
    Explanations

    phrases enclosed by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks, indicating direct speech or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alger
    -0.74
     derby
    -0.69
     posting
    -0.69
     publishing
    -0.66
     fury
    -0.65
     affiliate
    -0.65
     Gaal
    -0.65
     Crane
    -0.65
     seasoned
    -0.64
     shaking
    -0.64
    POSITIVE LOGITS
    almost
    1.10
    every
    1.09
    extremely
    1.03
    little
    1.02
    highly
    1.01
    moderate
    1.00
    self
    1.00
    super
    1.00
    never
    0.99
    their
    0.99
    Activations Density 0.134%

    No Known Activations