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. 5-RES-JB
    6. 16943
    Prev
    Next
    INDEX
    Explanations

    mentions of specific car models, particularly Tesla's Model X and Model S

    oai_token-act-pair · gpt-3.5-turbo

    specific model names and significant figures associated with Tesla and notable individuals

    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
     warr
    -0.69
    ream
    -0.67
     NAD
    -0.65
     TAM
    -0.63
     NI
    -0.63
     Tav
    -0.62
    NR
    -0.62
    iosyn
    -0.61
    msg
    -0.61
     Fischer
    -0.60
    POSITIVE LOGITS
    âĦ¢
    0.84
    culosis
    0.84
    wagen
    0.79
    utra
    0.77
    atoes
    0.75
    ®
    0.72
    Cola
    0.71
    ®,
    0.69
    âĦ¢:
    0.69
    ;;;;;;;;;;;;
    0.68
    Activations Density 0.212%

    No Known Activations