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. 12-RES-JB
    6. 17743
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial funding and budgeting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    forms of the verb "to be" and references to funding or financial allocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.76
    ModLoader
    -0.74
     srfAttach
    -0.72
    itect
    -0.71
    LER
    -0.68
    ital
    -0.68
    endiary
    -0.66
    culosis
    -0.66
    ricanes
    -0.65
    iants
    -0.65
    POSITIVE LOGITS
     spent
    1.31
     redistributed
    1.31
     invested
    1.27
     reinvest
    1.23
     allocated
    1.22
     expended
    1.21
     deposited
    1.17
     diverted
    1.17
     redirected
    1.15
     distributed
    1.15
    Activations Density 0.182%

    No Known Activations