INDEX

Explanations

names of specific organizations or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to organizations, institutions, and news entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.81

ĻĤ

-0.74

ItemImage

-0.66

ĪĴ

-0.65

iannopoulos

-0.64

 traumatic

-0.63

itably

-0.63

ierrez

-0.63

 nonprofits

-0.63

 paste

-0.62

POSITIVE LOGITS

 Room

0.92

 Graveyard

0.86

 Fathers

0.84

oran

0.80

 Committee

0.79

 Gazette

0.78

Bank

0.77

osphere

0.77

 Clause

0.75

Era

0.75

Activations Density 0.242%

names of specific organizations or entities

proper nouns related to organizations, institutions, and news entities

No Comments

No Known Activations