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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 18016
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing tasks or actions without certain requirements or hindrances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence of requirements or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.73
    estern
    -0.71
     largeDownload
    -0.69
    auri
    -0.69
    DragonMagazine
    -0.65
    âĹ¼
    -0.64
     ASA
    -0.63
    ERG
    -0.62
    Draft
    -0.60
    hement
    -0.59
    POSITIVE LOGITS
     anymore
    1.09
     nor
    1.03
     beforehand
    0.93
     themselves
    0.90
     whatsoever
    0.87
     oneself
    0.85
     slightest
    0.83
     necessarily
    0.81
    })
    0.75
     altogether
    0.74
    Activations Density 0.749%

    No Known Activations