INDEX

Explanations

words related to emotions of feeling

oai_token-act-pair · gpt-3.5-turbo

expressions of emotional states or feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ciating

-0.71

orem

-0.68

esan

-0.67

 Tactics

-0.67

photos

-0.66

çĦ

-0.65

encing

-0.64

ades

-0.62

zhen

-0.62

ffe

-0.62

POSITIVE LOGITS

 uneasy

1.09

 compelled

1.06

 comfortable

1.05

 ashamed

1.02

 confident

1.01

 uncomfortable

0.99

 nervous

0.98

 obligated

0.94

 discomfort

0.93

 sorry

0.92

Activations Density 0.049%

words related to emotions of feeling

expressions of emotional states or feelings

No Comments

No Known Activations