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. 6-RES-JB
    6. 8235
    Prev
    Next
    INDEX
    Explanations

    phrases instructing to "get" something

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withd
    -0.61
     defe
    -0.61
    pled
    -0.59
     experiment
    -0.58
    pard
    -0.57
     evoke
    -0.56
    è¦ļéĨĴ
    -0.56
     taboo
    -0.54
     portray
    -0.54
    bery
    -0.54
    POSITIVE LOGITS
     rid
    1.16
    TING
    1.10
    cloneembedreportprint
    0.93
    away
    0.92
    aways
    0.83
    ãĥ³ãĤ¸
    0.77
    ters
    0.77
     Rid
    0.75
    zl
    0.73
     Away
    0.73
    Activations Density 0.039%

    No Known Activations