© 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. 4381
    Prev
    Next
    INDEX
    Explanations

    specific years or dates

    oai_token-act-pair · gpt-3.5-turbo

    the word "In" at the beginning of sentences

    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
     behav
    -0.77
     ingred
    -0.77
     lett
    -0.75
     spoil
    -0.66
     brands
    -0.64
     entrants
    -0.64
     learners
    -0.64
     lodged
    -0.64
     heights
    -0.64
     dam
    -0.63
    POSITIVE LOGITS
    ventory
    1.44
    cluding
    1.42
    clusion
    1.29
    juries
    1.27
    clusive
    1.26
    strument
    1.26
    cluded
    1.26
    jured
    1.25
    visible
    1.22
    jury
    1.20
    Activations Density 0.159%

    No Known Activations