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. 16805
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various aspects of decision-making and conditions surrounding choices

    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
     sidx
    -0.64
     helicop
    -0.60
     nutshell
    -0.60
    liest
    -0.57
    aho
    -0.57
    uben
    -0.54
    iann
    -0.51
     bunny
    -0.51
    icer
    -0.50
    xton
    -0.50
    POSITIVE LOGITS
     Flavoring
    0.71
    Reviewer
    0.63
    aft
    0.62
    itars
    0.62
    akens
    0.61
     Dish
    0.57
     CLR
    0.56
     Rouhani
    0.56
    Redd
    0.56
    âĢ¢âĢ¢
    0.55
    Activations Density 1.146%

    No Known Activations