INDEX

Explanations

references to diversity in various contexts

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

mentions of diversity or varied groups of people/things

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

çĶ°

-0.74

rol

-0.74

WARD

-0.73

FORE

-0.73

ENA

-0.71

WAR

-0.68

Ob

-0.66

 clicked

-0.65

Removed

-0.63

rollers

-0.63

POSITIVE LOGITS

ively

0.99

ortment

0.92

mble

0.89

iveness

0.89

 assemb

0.88

iated

0.86

 perspectives

0.86

 genders

0.85

 avenues

0.84

 viewpoints

0.83

Activations Density 0.027%

references to diversity in various contexts

mentions of diversity or varied groups of people/things

No Comments

No Known Activations