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. 17597
    Prev
    Next
    INDEX
    Explanations

    large numbers or numerical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics, particularly those related to populations or quantities

    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
    ħĭ
    -0.70
     brut
    -0.65
    ESE
    -0.64
     convergence
    -0.62
     behav
    -0.62
     scrut
    -0.61
     pigeon
    -0.61
     ausp
    -0.59
     shell
    -0.58
     Dickinson
    -0.58
    POSITIVE LOGITS
    Downloadha
    0.96
    pees
    0.95
    ilts
    0.75
    coins
    0.75
    abytes
    0.74
    essions
    0.71
    ptoms
    0.71
     pounds
    0.71
    tumblr
    0.71
    sic
    0.69
    Activations Density 0.271%

    No Known Activations