INDEX

Explanations

words related to physical actions and exclamations

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

è¦ļéĨĴ

-0.69

 battleground

-0.67

 formerly

-0.67

 Associated

-0.66

senal

-0.65

 Proceedings

-0.63

BMC

-0.63

 influential

-0.62

¿½

-0.60

 encomp

-0.60

POSITIVE LOGITS

oooo

1.06

eeee

1.05

EEEE

1.03

aaaa

1.01

mmmm

0.99

mmm

0.95

hhhh

0.95

rily

0.95

hetically

0.95

HHHH

0.94

Activations Density 0.356%

words related to physical actions and exclamations

proper nouns or names within the text

No Comments

No Known Activations