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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4080
    Prev
    Next
    INDEX
    Explanations

    phrases related to the remainder or remaining part of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "remainder" and related conclusions in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amping
    -0.80
    edo
    -0.74
    eyes
    -0.69
     breasts
    -0.64
    amped
    -0.64
    vet
    -0.64
    lee
    -0.64
     nipples
    -0.60
    cer
    -0.60
    ducers
    -0.59
    POSITIVE LOGITS
    swer
    0.90
    ãĤ¼ãĤ¦ãĤ¹
    0.80
    ĸļ
    0.79
    phabet
    0.77
    ;}
    0.76
     remainder
    0.76
    recated
    0.74
    WER
    0.73
    é»Ĵ
    0.71
    VERTISEMENT
    0.70
    Activations Density 0.014%

    No Known Activations