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. 0-RES-JB
    6. 23049
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or change

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and similar verb forms, particularly focusing on the suffix 'ing'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mech
    -0.78
     Izan
    -0.68
     minions
    -0.66
     alive
    -0.66
     files
    -0.65
     controllers
    -0.61
     tanks
    -0.60
     formation
    -0.60
     file
    -0.60
     reproduction
    -0.60
    POSITIVE LOGITS
    inge
    4.68
    inges
    2.43
    inged
    1.64
    inging
    1.31
    inkle
    1.20
    ringe
    1.14
    ingle
    1.12
    uden
    1.07
     binge
    1.02
    edi
    0.99
    Activations Density 0.011%

    No Known Activations