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. 19121
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of intention or purpose

    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
    tnc
    -0.71
     Solitaire
    -0.71
    PASS
    -0.71
    --------------------------------------------------------
    -0.71
    NetMessage
    -0.69
    ------------------------------------------------
    -0.68
    Column
    -0.68
     Towns
    -0.68
    Edward
    -0.67
    Physical
    -0.67
    POSITIVE LOGITS
     aim
    0.95
    lessly
    0.95
    atory
    0.92
    eers
    0.91
    emouth
    0.85
     aiming
    0.84
     Aim
    0.81
    posts
    0.80
    gha
    0.80
    chens
    0.77
    Activations Density 0.010%

    No Known Activations