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. 3-RES-JB
    6. 18799
    Prev
    Next
    INDEX
    Explanations

    references to the company Ford

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ford"

    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
     Flavoring
    -0.84
    ablishment
    -0.84
    sembly
    -0.74
    laus
    -0.73
    udic
    -0.71
     Seym
    -0.69
    vironment
    -0.68
     sidx
    -0.68
    hemat
    -0.67
    anwhile
    -0.65
    POSITIVE LOGITS
    ham
    1.04
    shire
    0.97
    ragon
    0.91
     Motor
    0.83
    bies
    0.81
    clad
    0.81
    Ford
    0.80
     Ford
    0.78
     Mustang
    0.78
    rera
    0.72
    Activations Density 0.007%

    No Known Activations