INDEX

Explanations

proper nouns seemingly related to actors, characters, or productions, particularly focused on "Kaufman" and "Crane."

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of a specific character's name

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

xon

-0.74

MpServer

-0.68

CHO

-0.68

Balt

-0.62

ãĥīãĥ©ãĤ´ãĥ³

-0.62

 Lumia

-0.61

ãĥ³ãĤ¸

-0.61

pus

-0.61

Interstitial

-0.61

senal

-0.60

POSITIVE LOGITS

erent

1.11

irms

1.01

mpeg

1.00

ords

1.00

ees

0.98

erences

0.96

rey

0.93

erential

0.91

etch

0.90

iculty

0.90

Activations Density 0.014%

proper nouns seemingly related to actors, characters, or productions, particularly focused on "Kaufman" and "Crane."

the repeated mention of a specific character's name

No Comments

No Known Activations