INDEX

Explanations

proper nouns related to people, places, and things

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.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

ers

-0.77

ured

-0.76

ELS

-0.63

hedral

-0.63

»Ĵ

-0.63

ĵĺ

-0.63

ership

-0.62

 Gazette

-0.62

erest

-0.61

urer

-0.59

POSITIVE LOGITS

rors

1.25

gency

1.10

lein

1.06

jee

1.04

idan

1.02

ror

0.98

idge

0.98

getic

0.95

geist

0.95

maid

0.94

Activations Density 2.629%

proper nouns related to people, places, and things

No Comments

No Known Activations