INDEX

Explanations

phrases related to existence or presence

oai_token-act-pair · gpt-3.5-turbo

common conjunctions and phrases indicating inclusion or addition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

enance

-0.82

Ĥİ

-0.69

ãĤ´ãĥ³

-0.67

advertising

-0.62

ãĥ³ãĤ¸

-0.60

isin

-0.60

owered

-0.58

NR

-0.56

 IMAGES

-0.55

heartedly

-0.55

POSITIVE LOGITS

 somet

0.75

 plenty

0.72

abilities

0.72

 ranging

0.69

 besides

0.67

some

0.67

 none

0.66

abouts

0.65

enough

0.65

 lots

0.64

Activations Density 0.602%

phrases related to existence or presence

common conjunctions and phrases indicating inclusion or addition

No Comments

No Known Activations