INDEX

Explanations

phrases indicating contrast or emphasis

oai_token-act-pair · gpt-3.5-turbo

phrases that express limitation or negation

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

osion

-0.72

cies

-0.69

insula

-0.65

 VIDEOS

-0.62

ctors

-0.60

 Increases

-0.59

ortmund

-0.59

 Blaz

-0.58

soType

-0.58

UW

-0.57

POSITIVE LOGITS

forth

0.92

 employed

0.74

been

0.74

 considered

0.73

 confined

0.71

 entertained

0.70

 immortal

0.70

ãĥĩãĤ£

0.68

agree

0.68

always

0.67

Activations Density 0.197%

phrases indicating contrast or emphasis

phrases that express limitation or negation

No Comments

No Known Activations