Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 19722
    Prev
    Next
    INDEX
    Explanations

    references to a particular piece of text starting with "This" or mentions of an individual

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "This" or refer to actions or statements made by specific people

    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
    CVE
    -0.70
     mercury
    -0.68
     xp
    -0.66
     filler
    -0.64
     straw
    -0.63
     cutter
    -0.62
     foil
    -0.62
     usb
    -0.61
     blender
    -0.59
    VERTISEMENT
    -0.59
    POSITIVE LOGITS
    anmar
    0.91
    estine
    0.78
    chwitz
    0.72
    resa
    0.70
    jriwal
    0.69
    ulty
    0.69
    [/
    0.69
    âĢİ
    0.69
    monton
    0.68
    psey
    0.68
    Activations Density 0.326%

    No Known Activations