INDEX

Explanations

words related to personal preferences and likes

oai_token-act-pair · gpt-3.5-turbo

expressions of love or strong affection towards various subjects

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

qqa

-0.70

utor

-0.65

imester

-0.65

URR

-0.64

 Siberian

-0.64

 prelim

-0.63

Corp

-0.62

 strat

-0.61

uto

-0.60

TIME

-0.60

POSITIVE LOGITS

 hates

0.95

hate

0.86

olini

0.85

 hating

0.83

 rejoice

0.83

 cherish

0.79

 loves

0.78

 despise

0.77

 hate

0.76

 actionGroup

0.76

Activations Density 0.555%

words related to personal preferences and likes

expressions of love or strong affection towards various subjects

No Comments

No Known Activations