Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1044
    Prev
    Next
    INDEX
    Explanations

    verbs related to various forms of action

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles indicating actions or states related to movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deal
    -0.69
    eria
    -0.66
    onsense
    -0.64
    tel
    -0.64
    condition
    -0.63
    ont
    -0.63
    fortunately
    -0.61
    odor
    -0.60
    so
    -0.59
    los
    -0.59
    POSITIVE LOGITS
    HAM
    0.66
    WithNo
    0.63
    redients
    0.62
     suspic
    0.62
     hay
    0.62
    IRD
    0.61
     spree
    0.61
     Rohing
    0.60
    allowed
    0.59
    anchester
    0.58
    Activations Density 0.343%

    No Known Activations