INDEX

Explanations

mentions of a specific location or entity named "Lim"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãģ®éŃĶ

-0.80

ãĤ«

-0.77

ALK

-0.75

WD

-0.72

 Chronicle

-0.72

ãĤ¢ãĥ«

-0.71

Discuss

-0.71

Kent

-0.70

NEWS

-0.69

BOOK

-0.69

POSITIVE LOGITS

 satell

1.08

psons

1.06

undai

1.01

oshenko

0.98

orously

0.93

jriwal

0.93

reditary

0.92

edom

0.92

Lim

0.91

mbuds

0.90

Activations Density 0.008%

mentions of a specific location or entity named "Lim"

No Comments

No Known Activations