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. 2618
    Prev
    Next
    INDEX
    Explanations

    hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links

    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
     Morse
    -0.77
     destro
    -0.69
     Morales
    -0.67
     trave
    -0.67
    secut
    -0.65
     Speedway
    -0.65
     Sakuya
    -0.62
    NetMessage
    -0.62
    Ͻ
    -0.61
     deceive
    -0.61
    POSITIVE LOGITS
    ://
    1.57
    doi
    1.03
    :/
    0.98
    natureconservancy
    0.95
    archive
    0.88
    twitter
    0.83
     https
    0.80
     www
    0.76
    docs
    0.75
     http
    0.74
    Activations Density 0.006%

    No Known Activations