© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 3627
    Prev
    Next
    INDEX
    Explanations

    verbs related to curation, utility, and functionality

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the verb "serve" and its variations to indicate purpose or function

    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
    pex
    -0.69
    luaj
    -0.68
     inspected
    -0.66
    gins
    -0.62
    vu
    -0.62
    clone
    -0.62
    ascus
    -0.60
    verse
    -0.59
    ibliography
    -0.58
    hood
    -0.57
    POSITIVE LOGITS
     âĶľ
    0.74
     purpose
    0.71
     purposes
    0.70
     interests
    0.70
    ential
    0.66
    entially
    0.66
    Cra
    0.65
     serve
    0.65
    umes
    0.65
     objectives
    0.64
    Activations Density 0.036%

    No Known Activations