INDEX

Explanations

instances of the word "Five" or numbers related to five in various contexts

oai_token-act-pair · gpt-3.5-turbo

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

swick

-0.67

 Hort

-0.66

icol

-0.62

swer

-0.61

xual

-0.61

ophon

-0.60

ppo

-0.60

worldly

-0.59

urger

-0.58

bered

-0.58

POSITIVE LOGITS

Thirty

1.23

0.81

âĺħ

0.80

 ILCS

0.80

0.79

th

0.79

pb

0.73

ŃĶ

0.72

 gallon

0.72

Activations Density 0.134%

instances of the word "Five" or numbers related to five in various contexts

No Comments

No Known Activations