INDEX

Explanations

phrases related to gaps and disparities

oai_token-act-pair · gpt-3.5-turbo

references to various types of gaps, particularly socioeconomic or systemic disparities

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

der

-0.74

vez

-0.70

abad

-0.69

ovy

-0.64

cause

-0.64

rich

-0.63

mberg

-0.62

Die

-0.62

da

-0.60

oran

-0.60

POSITIVE LOGITS

 between

1.01

wid

1.00

gap

0.94

 widened

0.90

between

0.85

 Between

0.82

 gaps

0.81

 widen

0.80

Gap

0.79

 separating

0.77

Activations Density 0.034%

phrases related to gaps and disparities

references to various types of gaps, particularly socioeconomic or systemic disparities

No Comments

No Known Activations