INDEX

Explanations

proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

the word "That" in various contexts, indicating its importance in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

emis

-0.82

NAS

-0.78

ãĥ¼ãĥĨ

-0.75

¶ħ

-0.72

ATURES

-0.71

ãĤ¹ãĥĪ

-0.71

ģĸ

-0.71

atur

-0.69

¥ŀ

-0.69

pring

-0.68

POSITIVE LOGITS

 sounds

1.18

guy

1.13

 sucks

1.13

ain

1.12

's

1.10

 doesn

1.04

 wasn

1.01

 doesnt

1.00

 reminds

0.97

 sounded

0.97

Activations Density 0.115%

proper nouns or specific names

the word "That" in various contexts, indicating its importance in the text

No Comments

No Known Activations