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. 18781
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state of ongoing or continuous action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions or actions that should continue until a specific outcome is achieved

    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
     Cosponsors
    -0.73
    <?
    -0.73
     RSS
    -0.70
     Slate
    -0.67
     Holding
    -0.66
    @#&
    -0.65
     ``
    -0.64
     Declaration
    -0.64
    Reviewer
    -0.63
     Canaveral
    -0.63
    POSITIVE LOGITS
     reaches
    0.82
     ceases
    0.76
     perfected
    0.71
     disapp
    0.69
     arrives
    0.69
     mat
    0.69
    icka
    0.68
     arrive
    0.66
     settles
    0.66
     finally
    0.66
    Activations Density 0.138%

    No Known Activations