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. 5825
    Prev
    Next
    INDEX
    Explanations

    phrases related to persistence or determination

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use the term "down" in various contexts

    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
    thing
    -0.71
    thy
    -0.67
    qua
    -0.64
    owan
    -0.63
    mong
    -0.62
    çͰ
    -0.62
    kefeller
    -0.61
    digy
    -0.61
    /-
    -0.60
     Tyler
    -0.60
    POSITIVE LOGITS
    stairs
    0.97
    grading
    0.95
    graded
    0.89
    grades
    0.83
     stairs
    0.80
    esters
    0.79
    inately
    0.77
     srf
    0.75
    edly
    0.74
    wards
    0.72
    Activations Density 0.038%

    No Known Activations