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. 4-RES-JB
    6. 5051
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Tesla"

    oai_token-act-pair · gpt-3.5-turbo

    references to the company Tesla and its products or related events

    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
    ãĥĥãĥĪ
    -0.82
    olulu
    -0.74
     Kerry
    -0.66
    glers
    -0.66
    geries
    -0.64
    aci
    -0.64
    meaning
    -0.64
    enance
    -0.62
    ressing
    -0.62
    yip
    -0.61
    POSITIVE LOGITS
     Motors
    1.19
     Coil
    0.84
    Tesla
    0.79
     coils
    0.77
     Musk
    0.77
     Tesla
    0.76
    Mot
    0.75
     coil
    0.74
    Mobil
    0.74
    boat
    0.70
    Activations Density 0.010%

    No Known Activations