INDEX

Explanations

references to long-lasting impacts or influences, often of historical or cultural significance

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "legacy."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

owler

-0.77

tics

-0.77

acus

-0.75

anooga

-0.74

ramid

-0.74

bians

-0.73

earcher

-0.71

aber

-0.71

kers

-0.70

aleigh

-0.69

POSITIVE LOGITS

 legacy

1.08

 Legacy

0.77

 baggage

0.77

stones

0.73

arily

0.71

lore

0.69

 bearer

0.68

 writ

0.65

emonic

0.65

 ingrained

0.64

Activations Density 0.022%

references to long-lasting impacts or influences, often of historical or cultural significance

references to the concept of "legacy."

No Comments

No Known Activations