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. 9-RES-JB
    6. 777
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    references to data structures and storage in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.83
     paving
    -0.70
     gearing
    -0.65
     resil
    -0.65
     priesthood
    -0.64
     NTS
    -0.61
     mitigating
    -0.61
     stabil
    -0.61
     foregoing
    -0.61
     detrim
    -0.61
    POSITIVE LOGITS
    _
    1.42
    Count
    1.06
    Number
    1.02
     =
    1.00
    Of
    1.00
    Names
    0.98
    Obj
    0.97
    Dir
    0.97
    Flags
    0.96
    Size
    0.96
    Activations Density 0.143%

    No Known Activations