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. 5055
    Prev
    Next
    INDEX
    Explanations

    locations or settings within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their occurrences in various contexts

    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
    NOW
    -0.63
    CLASSIFIED
    -0.61
    BUS
    -0.61
     booked
    -0.60
    MORE
    -0.60
     debuted
    -0.59
    0000000000000000
    -0.59
     bolted
    -0.59
    ICO
    -0.58
    Champ
    -0.57
    POSITIVE LOGITS
     accordance
    1.26
     relation
    1.20
    escap
    1.19
     regards
    1.19
     conjunction
    1.15
     lieu
    1.15
    clus
    1.14
     situ
    1.11
     spite
    1.10
    effic
    1.08
    Activations Density 0.508%

    No Known Activations