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. 10-RES-JB
    6. 8890
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or requirements that need to be met before specific actions can be taken

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and discussions about timing or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iHUD
    -0.69
    ãĤ§
    -0.59
    ãĥĭ
    -0.58
     Equip
    -0.56
    ãĤ¨ãĥ«
    -0.55
    umbn
    -0.54
    RAG
    -0.54
    éĹĺ
    -0.54
    ãĤ½
    -0.54
     è£ıè
    -0.53
    POSITIVE LOGITS
     did
    1.41
     does
    1.38
    did
    1.24
     do
    1.21
     Does
    1.12
    does
    1.09
     are
    1.07
     DOES
    1.02
     will
    1.00
     Did
    0.99
    Activations Density 0.207%

    No Known Activations