© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17597
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal or social rules and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accountability or legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twist
    -0.68
     Extend
    -0.67
    rawdownloadcloneembedreportprint
    -0.66
    #$
    -0.64
     childbirth
    -0.63
    ĸļ
    -0.62
    udge
    -0.59
    esta
    -0.59
    pent
    -0.58
    Length
    -0.58
    POSITIVE LOGITS
     doomed
    1.24
     disqualified
    1.22
     liable
    1.21
     ineligible
    1.12
     labelled
    1.09
     labeled
    1.09
     punished
    1.08
     considered
    1.08
     ridiculed
    1.07
     termed
    1.05
    Activations Density 0.170%

    No Known Activations