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. 12680
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to a specific person named Elliston

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Ell

    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
    ItemTracker
    -0.87
    ãĥ£
    -0.81
    POR
    -0.74
    ========
    -0.73
    oglu
    -0.72
    VB
    -0.71
    PRES
    -0.71
    Graphics
    -0.70
    EFF
    -0.69
    KING
    -0.68
    POSITIVE LOGITS
    ipt
    1.16
    izabeth
    1.09
     Ell
    1.07
    sworth
    1.02
    igible
    0.93
    inia
    0.89
    idays
    0.87
    inel
    0.85
    yss
    0.84
    owship
    0.84
    Activations Density 0.010%

    No Known Activations