INDEX

Explanations

terms containing the prefix "non-"

oai_token-act-pair · gpt-3.5-turbo

mentions of "non-" prefixes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Tycoon

-0.99

 Oaks

-0.79

 Showdown

-0.76

 Grind

-0.75

 Banner

-0.73

 Grill

-0.70

 Spoon

-0.70

 Gardens

-0.68

 Sparrow

-0.68

 McGee

-0.68

POSITIVE LOGITS

chal

1.15

linear

1.12

etheless

1.11

profit

1.07

technical

1.07

fiction

1.06

zero

1.05

verbal

1.05

lethal

1.03

threatening

1.02

Activations Density 0.037%

terms containing the prefix "non-"

mentions of "non-" prefixes in various contexts

No Comments

No Known Activations