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. 24420
    Prev
    Next
    INDEX
    Explanations

    URLs indicated by "http://"

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web addresses

    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
     sided
    -0.80
     confir
    -0.77
     Palestin
    -0.76
    ©¶æ
    -0.75
    etheless
    -0.72
     unsus
    -0.71
     Labrador
    -0.70
     depos
    -0.69
     deceive
    -0.69
     deported
    -0.68
    POSITIVE LOGITS
    www
    1.56
    natureconservancy
    1.52
    ://
    1.46
    doi
    1.08
    goo
    0.98
    archive
    0.98
    youtu
    0.98
    docs
    0.97
    wcsstore
    0.97
    :/
    0.97
    Activations Density 0.012%

    No Known Activations