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. 6954
    Prev
    Next
    INDEX
    Explanations

    words related to imitating or emulating

    oai_token-act-pair · gpt-3.5-turbo

    words related to imitation and mimicry

    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
    band
    -0.76
    endale
    -0.72
    uid
    -0.70
    Frag
    -0.69
    asse
    -0.69
    Present
    -0.68
    elle
    -0.67
    dies
    -0.66
    stone
    -0.66
    enders
    -0.66
    POSITIVE LOGITS
     likeness
    0.96
     imitation
    0.88
     emulate
    0.86
     imitate
    0.85
    natureconservancy
    0.80
    iliar
    0.80
    ãĤ¼ãĤ¦ãĤ¹
    0.69
     idol
    0.68
     mock
    0.67
     copyrighted
    0.67
    Activations Density 0.053%

    No Known Activations