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. 18262
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles in verb forms

    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
    spot
    -0.68
    omet
    -0.63
    respond
    -0.59
     Baz
    -0.58
     executing
    -0.58
     Hig
    -0.57
    playing
    -0.57
     resting
    -0.57
    aligned
    -0.56
    ãĥĨ
    -0.55
    POSITIVE LOGITS
    redients
    1.14
    HAM
    0.96
    ulate
    0.86
    tons
    0.79
     conventions
    0.74
    ham
    0.73
     toilets
    0.72
     machines
    0.70
    icate
    0.70
     sessions
    0.68
    Activations Density 0.178%

    No Known Activations