© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 20034
    Prev
    Next
    INDEX
    Explanations

    phrases related to relocating or moving to a new place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" as a preposition or infinitive marker

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

    No Comments

    Negative Logits
     payable
    -0.63
    ingly
    -0.62
     hairc
    -0.60
    RF
    -0.60
    sle
    -0.59
     testim
    -0.59
    PLIED
    -0.58
     thereof
    -0.57
     testimonies
    -0.57
     SERV
    -0.56
    POSITIVE LOGITS
     accommodate
    0.91
    pload
    0.87
     grips
    0.82
     eliminate
    0.80
     abolish
    0.80
     maximize
    0.78
     become
    0.78
    ilet
    0.76
     pursue
    0.76
     reinforce
    0.76
    Activations Density 0.194%

    No Known Activations