INDEX

Explanations

phrases indicating agreement or similarity

oai_token-act-pair · gpt-3.5-turbo

auxiliary verbs indicating actions or states of being

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

QB

-0.73

opian

-0.66

dream

-0.66

colo

-0.65

jab

-0.64

OH

-0.63

Words

-0.62

places

-0.60

 incorpor

-0.59

bip

-0.58

POSITIVE LOGITS

Geh

0.72

 others

0.66

 countless

0.65

racuse

0.63

essage

0.63

 Doomsday

0.61

 Greenberg

0.61

SHARE

0.60

OTAL

0.59

 dozens

0.59

Activations Density 0.044%

phrases indicating agreement or similarity

auxiliary verbs indicating actions or states of being

No Comments

No Known Activations