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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 23026
    Prev
    Next
    INDEX
    Explanations

    personal names within a context of narrative or dialogue

    oai_token-act-pair · gpt-3.5-turbo

    words associated with discussions of morality or ethical reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pestic
    -0.88
     mathemat
    -0.86
     horizont
    -0.78
    iatus
    -0.77
    raints
    -0.76
     incorpor
    -0.75
     myster
    -0.75
     explan
    -0.75
     disadvant
    -0.74
     welf
    -0.73
    POSITIVE LOGITS
    ï¸ı
    1.00
    âĹ¼
    0.91
    ãĥĥãĥī
    0.91
    rd
    0.88
    deg
    0.86
    log
    0.86
    ĺ
    0.84
    fter
    0.83
    hair
    0.78
    é¾į
    0.78
    Activations Density 0.035%

    No Known Activations