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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11482
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Sl9."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Sl" 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
    ãģ®éŃĶ
    -0.94
    ICLE
    -0.85
    enegger
    -0.82
    æĪ¦
    -0.72
    è»
    -0.71
    bell
    -0.70
    åĤ
    -0.68
    æĦ
    -0.66
    èĪ
    -0.66
    ||||
    -0.66
    POSITIVE LOGITS
    ugg
    1.17
    ickers
    1.11
    ips
    1.10
    ashes
    1.09
    udge
    1.08
    ipper
    1.06
    icker
    1.05
    irts
    1.05
    acker
    1.03
    oppy
    1.03
    Activations Density 0.017%

    No Known Activations