INDEX

Explanations

phrases related to the concept of something being "based on" a particular idea, concept, or data

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of being "based on" something

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

İĭ

-0.62

anka

-0.59

apes

-0.59

 Kills

-0.58

 Appears

-0.58

 Flavoring

-0.57

zzle

-0.57

adobe

-0.56

Tid

-0.56

eden

-0.56

POSITIVE LOGITS

 loosely

1.21

 upon

1.18

 squarely

1.06

 solely

1.05

 entirely

1.02

 purely

1.00

 principally

0.93

 largely

0.91

 primarily

0.91

 around

0.90

Activations Density 0.058%

phrases related to the concept of something being "based on" a particular idea, concept, or data

phrases that emphasize the concept of being "based on" something

No Comments

No Known Activations