INDEX

Explanations

company or organization names ending with an apostrophe followed by a lowercase 's'

oai_token-act-pair · gpt-3.5-turbo

instances of plural nouns

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

docker

-0.72

Reviewed

-0.69

Picture

-0.66

ļéĨĴ

-0.65

 Volunte

-0.65

EVA

-0.62

 Reef

-0.62

irtual

-0.61

 Photograph

-0.60

 misunder

-0.60

POSITIVE LOGITS

selves

0.86

 youngest

0.76

 tallest

0.75

 princip

0.75

pecially

0.75

outhern

0.74

alty

0.74

ername

0.74

 birthplace

0.73

ELF

0.72

Activations Density 0.287%

company or organization names ending with an apostrophe followed by a lowercase 's'

instances of plural nouns

No Comments

No Known Activations