INDEX

Explanations

phrases related to negative feelings or situations, particularly those involving distress or disgust

oai_token-act-pair · gpt-3.5-turbo

terms related to distress or negative emotional states

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

theless

-0.85

FactoryReloaded

-0.68

frames

-0.67

 Falling

-0.65

phone

-0.65

FIELD

-0.65

ton

-0.63

deen

-0.63

FORE

-0.62

 briefs

-0.62

POSITIVE LOGITS

anced

1.25

illation

1.17

ributes

1.10

ancing

1.09

aste

1.05

ribut

1.00

illery

0.99

ogg

0.97

antly

0.95

ressing

0.93

Activations Density 0.019%

phrases related to negative feelings or situations, particularly those involving distress or disgust

terms related to distress or negative emotional states

No Comments

No Known Activations