INDEX

Explanations

phrases that imply strong emotional response or emphasis

oai_token-act-pair · gpt-3.5-turbo

prominent nouns and important phrases that signify attention or emphasis

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

 ÂŃ

-0.61

 thereto

-0.57

.","

-0.56

``

-0.56

SPONSORED

-0.54

.ï¿½

-0.54

 âĢ¦"

-0.54

 ï¿½

-0.54

 characterized

-0.52

.</

-0.51

POSITIVE LOGITS

odore

1.01

resa

1.00

xiety

0.90

bidden

0.87

swers

0.85

dinand

0.84

anmar

0.80

theless

0.78

otine

0.77

jamin

0.77

Activations Density 0.525%

phrases that imply strong emotional response or emphasis

prominent nouns and important phrases that signify attention or emphasis

No Comments

No Known Activations