INDEX

Explanations

phrases related to comparing differences between various concepts or entities

oai_token-act-pair · gpt-3.5-turbo

phrases that convey comparisons or distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bye

-0.80

OGR

-0.79

avascript

-0.74

dn

-0.74

nell

-0.73

ihilation

-0.72

der

-0.72

ãĤ¡

-0.71

igion

-0.70

idth

-0.70

POSITIVE LOGITS

 sexes

0.94

 genders

0.91

 halves

0.79

 those

0.74

 these

0.70

 eras

0.66

 what

0.66

 them

0.65

 Ware

0.61

 sender

0.60

Activations Density 0.042%

phrases related to comparing differences between various concepts or entities

phrases that convey comparisons or distinctions

No Comments

No Known Activations