© 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. 7-RES-JB
    11. 23745
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters, including breaking the law, court determinations, and workplace assessments

    oai_token-act-pair · gpt-3.5-turbo

    recurring conjunctions and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.62
    actionDate
    -0.61
    DX
    -0.61
    ventory
    -0.60
    dayName
    -0.60
    Contents
    -0.59
    Dust
    -0.59
     Powered
    -0.58
    Constructed
    -0.57
    doi
    -0.56
    POSITIVE LOGITS
     therefore
    1.44
     hence
    1.38
     thus
    1.38
     consequently
    1.37
     thereby
    1.31
     THEN
    1.20
     furthermore
    1.10
     secondly
    1.08
     subsequently
    0.99
     then
    0.97
    Activations Density 0.376%

    No Known Activations