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. 9259
    Prev
    Next
    INDEX
    Explanations

    phrases with the word 'and' in them

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" and its variations

    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
    hov
    -0.93
    ukong
    -0.86
    ouls
    -0.82
    acci
    -0.81
    cipled
    -0.68
    hatt
    -0.68
    ixel
    -0.68
    utra
    -0.66
    cients
    -0.65
    illac
    -0.65
    POSITIVE LOGITS
     maintenance
    0.81
     hence
    0.78
     therefore
    0.78
     subsistence
    0.76
     evaluation
    0.75
     consequently
    0.74
     chore
    0.72
    /
    0.72
     communications
    0.71
     consequ
    0.70
    Activations Density 0.428%

    No Known Activations