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. 3-RES-JB
    6. 2602
    Prev
    Next
    INDEX
    Explanations

    words related to typing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "typing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.77
    Ĭ±
    -0.72
    Aid
    -0.70
     Polaris
    -0.69
    apor
    -0.68
     Gors
    -0.68
     Lions
    -0.66
    ivals
    -0.66
     Ukrain
    -0.66
     Scient
    -0.63
    POSITIVE LOGITS
     typing
    1.08
    face
    1.05
     typed
    1.05
    faces
    0.98
     typew
    0.93
     scrolling
    0.91
    ocom
    0.82
     cursor
    0.82
     Typ
    0.80
    typ
    0.80
    Activations Density 0.016%

    No Known Activations