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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19780
    Prev
    Next
    INDEX
    Explanations

    phrases with repeated words or phrases with the construction 'as is'

    oai_token-act-pair · gpt-3.5-turbo

    the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istries
    -0.89
    chie
    -0.79
    rol
    -0.75
    {"
    -0.69
    ãģ®éŃĶ
    -0.69
    aukee
    -0.69
    incial
    -0.69
    jee
    -0.68
    ificate
    -0.67
    iard
    -0.65
    POSITIVE LOGITS
     evidenced
    0.92
     doubtless
    0.77
     presently
    0.71
     usual
    0.67
    agus
    0.64
     Bigfoot
    0.63
     implied
    0.62
    ftime
    0.60
    ©¶æ
    0.60
    ibrarian
    0.60
    Activations Density 0.028%

    No Known Activations