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. 11650
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns followed by specific nouns

    oai_token-act-pair · gpt-3.5-turbo

    plural forms of the letter 's' in different 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
     Hasan
    -0.72
     Presidents
    -0.72
     indemn
    -0.71
     boycot
    -0.67
     Grateful
    -0.62
     Suns
    -0.61
     Islamic
    -0.60
     Republican
    -0.59
     Ping
    -0.59
     Sinn
    -0.58
    POSITIVE LOGITS
    pecially
    1.14
    lightly
    1.13
    atisf
    1.11
    uddenly
    1.05
    ELF
    1.05
    ustainable
    1.02
    ources
    0.99
    omew
    0.99
    ustain
    0.98
    ̶
    0.94
    Activations Density 0.303%

    No Known Activations