INDEX

Explanations

quantitative comparisons using the word "than"

oai_token-act-pair · gpt-3.5-turbo

phrases involving comparisons related to quantity or level thresholds

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Juda

-0.72

 millenn

-0.71

 largeDownload

-0.65

uploads

-0.65

taboola

-0.64

olitan

-0.64

uther

-0.63

Eye

-0.62

owe

-0.62

 Palestin

-0.61

POSITIVE LOGITS

average

0.73

0.71

stellar

0.68

 contiguous

0.67

 Magicka

0.66

XXX

0.65

0.64

 compensated

0.63

angular

0.63

Activations Density 0.098%

quantitative comparisons using the word "than"

phrases involving comparisons related to quantity or level thresholds

No Comments

No Known Activations