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. 2-RES-JB
    6. 2718
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "rock"

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the substring "ock"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conflic
    -0.81
    undai
    -0.80
     citiz
    -0.74
     cryst
    -0.71
     reluct
    -0.71
     glim
    -0.70
     constitu
    -0.70
     refusal
    -0.70
    senal
    -0.69
    ccording
    -0.68
    POSITIVE LOGITS
    tails
    1.00
    strap
    0.91
    tail
    0.89
    STAR
    0.85
    ipel
    0.85
    ocks
    0.83
    ers
    0.83
    ings
    0.81
    lake
    0.81
    jay
    0.81
    Activations Density 0.009%

    No Known Activations