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. 0-RES-JB
    6. 9344
    Prev
    Next
    INDEX
    Explanations

    terms related to technology equipment, especially chargers and adapters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chargers and adapters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturdays
    -0.67
    LU
    -0.67
    witz
    -0.67
     overcrowd
    -0.66
     DEFENSE
    -0.66
    ynasty
    -0.63
     CLR
    -0.63
    jen
    -0.63
    FLAG
    -0.63
     IPM
    -0.63
    POSITIVE LOGITS
     charger
    1.33
    ac
    1.10
     charg
    0.97
    é¾įåĸļ士
    0.91
    acter
    0.78
    idon
    0.72
    acl
    0.70
    eur
    0.66
    bably
    0.64
    cephal
    0.64
    Activations Density 0.003%

    No Known Activations