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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 4086
    Prev
    Next
    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their usage in various contexts

    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
     Submission
    -0.66
     srfAttach
    -0.65
     meanwhile
    -0.62
     tong
    -0.62
     Allaah
    -0.61
     Tanz
    -0.61
     Fortune
    -0.59
     petertodd
    -0.59
     =================
    -0.59
     Hots
    -0.59
    POSITIVE LOGITS
    irs
    1.21
    gs
    1.15
    lling
    1.13
    ggles
    1.12
    ering
    1.11
    ses
    1.11
    conom
    1.10
    kes
    1.09
    icular
    1.08
    aps
    1.08
    Activations Density 1.209%

    No Known Activations