INDEX

Explanations

verbs indicating an action or intention

oai_token-act-pair · gpt-3.5-turbo

expressions related to actions or activities performed by the speaker

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

natureconservancy

-0.79

 Flavoring

-0.70

Catalog

-0.68

Grade

-0.68

meter

-0.67

ItemTracker

-0.66

Neg

-0.66

Links

-0.64

inventoryQuantity

-0.63

Newsletter

-0.62

POSITIVE LOGITS

icably

0.76

ĸļ

0.75

hyde

0.73

ividual

0.66

plin

0.66

REDACTED

0.63

erent

0.63

TRY

0.63

initely

0.61

 bragging

0.61

Activations Density 0.060%

verbs indicating an action or intention

expressions related to actions or activities performed by the speaker

No Comments

No Known Activations