INDEX

Explanations

groups or quantities of people or things

oai_token-act-pair · gpt-3.5-turbo

phrases indicating quantities or distributions involving groups of people or things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

emonium

-0.78

terson

-0.62

elsen

-0.61

atari

-0.61

ablishment

-0.60

-0.58

fuck

-0.58

herty

-0.57

ukong

-0.57

ahime

-0.57

POSITIVE LOGITS

 notably

1.19

 consisting

1.05

 comprising

1.04

 totaling

0.99

 including

0.98

 originating

0.97

including

0.94

 specializing

0.93

 citing

0.92

 representing

0.91

Activations Density 0.153%

groups or quantities of people or things

phrases indicating quantities or distributions involving groups of people or things

No Comments

No Known Activations