INDEX

Explanations

instances of the word 'a'

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" 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 @ 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

assisted

-0.86

OWS

-0.72

sheets

-0.69

anism

-0.69

enance

-0.68

Ott

-0.67

ographs

-0.67

tags

-0.66

Reviewed

-0.66

 Researchers

-0.66

POSITIVE LOGITS

lot

1.30

 possibility

1.14

 plethora

1.10

 tremendous

1.08

 tendency

1.06

LOT

1.06

 chance

1.03

 definite

1.02

 huge

0.98

 shortage

0.97

Activations Density 0.082%

instances of the word 'a'

the indefinite article "a" in various contexts

No Comments

No Known Activations