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. 0-RES-JB
    6. 5700
    Prev
    Next
    INDEX
    Explanations

    words related to interaction or connection between people or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ingle" and variations of the word "edi."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     robots
    -0.78
     Pens
    -0.71
     Rapt
    -0.69
     def
    -0.68
     options
    -0.65
     planetary
    -0.64
     alternatives
    -0.63
     Fuk
    -0.63
     robotics
    -0.63
     tanks
    -0.62
    POSITIVE LOGITS
    ingle
    4.41
    inkle
    1.30
    inge
    1.18
    angle
    1.17
    ingo
    1.11
    addle
    1.10
    izzle
    1.09
    oola
    1.01
    imity
    0.99
    hirt
    0.98
    Activations Density 0.018%

    No Known Activations