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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11117
    Prev
    Next
    INDEX
    Explanations

    references to the name "Courtney" and variations of the word "sweet."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or names related to events or activities

    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
    ãĥī
    -0.71
     Machines
    -0.70
     Typh
    -0.69
    stri
    -0.67
     Sil
    -0.67
     Nib
    -0.66
     humanoid
    -0.65
     Fib
    -0.65
     stagnant
    -0.65
    mob
    -0.64
    POSITIVE LOGITS
    ourt
    3.86
    ousse
    1.23
    zyk
    1.20
    pps
    1.12
     Bour
    1.11
    Court
    1.03
    ardon
    1.02
    $$
    1.02
    von
    1.01
    illac
    1.00
    Activations Density 0.058%

    No Known Activations