INDEX

Explanations

numerical ranges presented in the format "X-Y"

oai_token-act-pair · gpt-3.5-turbo

numerical values, particularly related to measurements and statistics

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

Negative Logits

ndra

-0.69

aida

-0.66

 bait

-0.66

andem

-0.65

sters

-0.64

 Kodi

-0.64

eworld

-0.64

 Creator

-0.63

vae

-0.63

 Balk

-0.61

POSITIVE LOGITS

degree

1.00

percent

0.97

ãĤ¼ãĤ¦ãĤ¹

0.89

MPH

0.86

 percentile

0.85

 Percent

0.84

pound

0.83

ãĥīãĥ©ãĤ´ãĥ³

0.82

å£«

0.81

0.78

Activations Density 0.125%

numerical ranges presented in the format "X-Y"

numerical values, particularly related to measurements and statistics

No Known Activations