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. 12657
    Prev
    Next
    INDEX
    Explanations

    strong emotions or opinions expressed in text

    oai_token-act-pair · gpt-3.5-turbo

    negative actions or statements related to inability or failure

    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
    Balance
    -0.75
     recip
    -0.68
    Tokens
    -0.67
    ueless
    -0.67
    each
    -0.66
    Higher
    -0.66
    Compared
    -0.65
    balance
    -0.64
    Someone
    -0.64
    SpaceEngineers
    -0.64
    POSITIVE LOGITS
    ashtra
    0.73
     meanwhile
    0.69
    notations
    0.68
     Bris
    0.65
     Slate
    0.64
     Zub
    0.63
     Tsarnaev
    0.62
     Phant
    0.62
     Eliot
    0.61
     Sut
    0.59
    Activations Density 0.547%

    No Known Activations