INDEX

Explanations

words related to discrepancies or differences between things

oai_token-act-pair · gpt-3.5-turbo

words related to discrepancies and disparities in data or context

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

trak

-0.84

Interstitial

-0.82

ovy

-0.81

hammad

-0.78

abad

-0.74

NetMessage

-0.69

rich

-0.68

bern

-0.65

ogy

-0.63

istan

-0.62

POSITIVE LOGITS

 discrepancy

0.97

 disparity

0.95

 proport

0.95

 discrepancies

0.95

 disparities

0.90

 ratios

0.88

 disproportion

0.84

 inequ

0.84

 discrep

0.83

 ratio

0.76

Activations Density 0.019%

words related to discrepancies or differences between things

words related to discrepancies and disparities in data or context

No Comments

No Known Activations