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. 1-RES-JB
    6. 11978
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical impact or force

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "knock" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Situation
    -0.76
     Archives
    -0.76
    RAM
    -0.73
    porting
    -0.73
     Offic
    -0.72
    communication
    -0.70
    pmwiki
    -0.70
     Prosecutors
    -0.69
    MSN
    -0.69
     Incident
    -0.69
    POSITIVE LOGITS
     knock
    1.42
     knocks
    1.09
     knocked
    1.02
     knocking
    0.94
     knockout
    0.92
     Knock
    0.90
    down
    0.81
    kn
    0.79
     inhibitors
    0.79
     inhibitor
    0.76
    Activations Density 0.009%

    No Known Activations