INDEX

Explanations

phrases related to emotions and emotional regulation

oai_token-act-pair · gpt-3.5-turbo

terms related to emotional regulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

essential

-0.67

iago

-0.65

Nex

-0.63

Dou

-0.62

 Municip

-0.61

unes

-0.61

holder

-0.61

 Monthly

-0.60

estones

-0.60

ardy

-0.60

POSITIVE LOGITS

 feelings

0.84

uate

0.84

otions

0.82

 emotions

0.82

uated

0.82

otion

0.81

 emotion

0.78

uations

0.78

atically

0.78

 contag

0.78

Activations Density 0.014%

phrases related to emotions and emotional regulation

terms related to emotional regulation

No Comments

No Known Activations