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. 5-RES-JB
    6. 20620
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making or taking a firm stand on a particular issue

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and connectors indicating relationships or actions

    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
    DragonMagazine
    -0.56
    andowski
    -0.55
    INESS
    -0.55
    edin
    -0.54
    hap
    -0.54
    NH
    -0.53
    orah
    -0.53
    okia
    -0.49
    imental
    -0.49
    verages
    -0.49
    POSITIVE LOGITS
     hers
    0.59
     Camel
    0.56
     Carbuncle
    0.51
     Ci
    0.51
    rium
    0.50
     theirs
    0.50
     ours
    0.50
     adulthood
    0.48
     Cain
    0.47
     Scots
    0.47
    Activations Density 1.309%

    No Known Activations