INDEX

Explanations

phrases related to negative emotions or conflicts

oai_token-act-pair · gpt-3.5-turbo

references to bitterness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

upload

-0.89

ORTS

-0.79

nesota

-0.79

inances

-0.79

ulhu

-0.78

icans

-0.76

ioch

-0.75

afort

-0.75

allows

-0.75

arlane

-0.75

POSITIVE LOGITS

 bitter

1.17

terness

1.17

 parting

1.06

 bitterness

0.99

 irony

0.91

 disappointment

0.88

 bitterly

0.88

spo

0.87

 defeat

0.87

 sweet

0.86

Activations Density 0.011%

phrases related to negative emotions or conflicts

references to bitterness in various contexts

No Comments

No Known Activations