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. 10-RES-JB
    6. 20807
    Prev
    Next
    INDEX
    Explanations

    words that contain the substring "ph"

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and specific medical or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constituent
    -0.69
     SB
    -0.63
     ingred
    -0.61
     srfAttach
    -0.59
     XL
    -0.57
    REL
    -0.57
     kittens
    -0.57
     constituents
    -0.57
    uties
    -0.56
     deviation
    -0.56
    POSITIVE LOGITS
    ilon
    0.92
    tainment
    0.89
    Reloaded
    0.88
    iquette
    0.82
    anasia
    0.81
    vironment
    0.81
    ipt
    0.80
    hemer
    0.79
    ascript
    0.79
    ionage
    0.78
    Activations Density 0.065%

    No Known Activations