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. 3-RES-JB
    6. 1691
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies

    oai_token-act-pair · gpt-3.5-turbo

    references to companies with "Ltd" in their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.92
    FACE
    -0.81
    \":
    -0.80
    actionDate
    -0.75
    States
    -0.74
    \\\\\\\\\\\\\\\\
    -0.74
    lled
    -0.74
    ÃįÃį
    -0.71
    =-=-=-=-=-=-=-=-
    -0.68
    wic
    -0.68
    POSITIVE LOGITS
    iffe
    1.09
     Ltd
    0.99
    orp
    0.99
    orporated
    0.97
    orea
    0.85
    rador
    0.84
    inia
    0.83
    iner
    0.81
    atta
    0.80
    enture
    0.79
    Activations Density 0.011%

    No Known Activations