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. 6-RES-JB
    6. 2347
    Prev
    Next
    INDEX
    Explanations

    actions and activities performed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    actions and activities that involve engagement or participation

    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
    si
    -0.83
    eria
    -0.69
    nings
    -0.69
    chev
    -0.69
    ibrary
    -0.66
    vu
    -0.66
     McDonnell
    -0.65
    cmp
    -0.65
    skin
    -0.64
    avage
    -0.64
    POSITIVE LOGITS
     oneself
    0.89
    redients
    0.76
     alike
    0.67
     hearts
    0.66
     yourself
    0.66
     habits
    0.64
     merry
    0.64
    quished
    0.62
    GGGGGGGG
    0.62
     Squid
    0.62
    Activations Density 0.200%

    No Known Activations