© 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. 20745
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "gr"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "gr" in various contexts, particularly relating to approval or endorsement

    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
    eers
    -0.81
    ĸļ
    -0.66
    66666666
    -0.65
     shortened
    -0.64
     caution
    -0.63
    WER
    -0.63
    doors
    -0.62
    mortem
    -0.62
     paperback
    -0.61
    phrine
    -0.61
    POSITIVE LOGITS
    iffin
    1.09
    illing
    1.09
    anted
    1.07
    ains
    1.07
    anting
    1.06
    asp
    1.04
    illed
    0.99
    ants
    0.99
    udge
    0.99
    udging
    0.99
    Activations Density 0.006%

    No Known Activations