Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 12380
    Prev
    Next
    INDEX
    Explanations

    verbs relating to taking care of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    special character tokens or placeholders indicating the end of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.72
    oppable
    -0.63
     Niet
    -0.63
    dating
    -0.62
    enegger
    -0.61
     Vaugh
    -0.61
    attering
    -0.60
    licted
    -0.60
    nown
    -0.59
    ãĤ´ãĥ³
    -0.58
    POSITIVE LOGITS
     RELEASE
    0.84
    ISE
    0.61
     GeForce
    0.59
    poses
    0.53
     Xperia
    0.52
    MEN
    0.51
     Ratio
    0.51
     USE
    0.50
    oreal
    0.50
     rescue
    0.50
    Activations Density 0.157%

    No Known Activations