Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 11279
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    words relating to a form of suffix or verb conjugation, particularly those ending in "ed" or "ing."

    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
    intosh
    -0.79
     WATCHED
    -0.73
    istan
    -0.69
    perty
    -0.69
    Products
    -0.67
    anni
    -0.66
    akespe
    -0.66
    akia
    -0.65
    ylum
    -0.65
    framework
    -0.61
    POSITIVE LOGITS
    eding
    0.93
    ication
    0.82
    uctor
    0.80
    irect
    0.76
    eded
    0.75
    vironment
    0.70
    uces
    0.70
    uce
    0.69
    velop
    0.69
    uced
    0.68
    Activations Density 0.019%

    No Known Activations