INDEX

Explanations

phrases indicating inclusivity or completeness

oai_token-act-pair · gpt-3.5-turbo

phrases that convey the concept of totality or entirety

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fenrir

-0.72

anova

-0.68

namese

-0.66

 Malf

-0.62

tis

-0.61

potion

-0.60

 Cumm

-0.59

 Tale

-0.57

 Savior

-0.57

 dwell

-0.57

POSITIVE LOGITS

ocating

0.89

 manner

0.89

 likelihood

0.88

onse

0.80

 vicinity

0.78

ĸļ

0.78

 precincts

0.78

uding

0.76

iance

0.76

usion

0.75

Activations Density 0.076%

phrases indicating inclusivity or completeness

phrases that convey the concept of totality or entirety

No Comments

No Known Activations