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. 2309
    Prev
    Next
    INDEX
    Explanations

    personal pronouns (especially "My") indicating possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "My"

    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
    itud
    -0.72
    س
    -0.67
    Balt
    -0.66
     Edison
    -0.65
    1080
    -0.65
    itect
    -0.65
    ãĥ´ãĤ¡
    -0.64
     apiece
    -0.64
    ulkan
    -0.63
    '."
    -0.62
    POSITIVE LOGITS
    anmar
    1.42
    stery
    1.35
    riad
    1.17
    self
    1.15
     own
    1.09
    ths
    1.08
    stic
    1.06
     apologies
    1.02
     favourite
    1.02
    opia
    1.01
    Activations Density 0.065%

    No Known Activations