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. 7-RES-JB
    6. 15418
    Prev
    Next
    INDEX
    Explanations

    words related to linguistic morphology, transformation, involvement in events or processes, and the concept of alteration or evolution

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or words ending in 'ing' and related suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Healer
    -0.76
     Immunity
    -0.74
     Hayden
    -0.74
     Defenders
    -0.71
     Hutchinson
    -0.70
     Companion
    -0.69
     Mellon
    -0.69
     Balanced
    -0.67
     Gingrich
    -0.66
     Simpson
    -0.66
    POSITIVE LOGITS
    rill
    1.10
    secut
    0.96
    ularity
    0.94
    ve
    0.94
    vered
    0.92
    pped
    0.92
    eless
    0.92
    ared
    0.92
    oldown
    0.92
    ped
    0.92
    Activations Density 0.160%

    No Known Activations