INDEX

Explanations

words related to locations, events, and possibly names ending with 'esh'

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

eering

-0.90

ertodd

-0.82

emort

-0.82

 carbohyd

-0.73

 reconc

-0.70

é¾įå¥ĳå£«

-0.67

eers

-0.64

 accur

-0.64

estamp

-0.64

STER

-0.63

POSITIVE LOGITS

merga

1.80

adow

1.14

awar

1.13

awk

1.02

arma

0.98

ifter

0.95

IFT

0.90

mun

0.90

adows

0.89

ivot

0.88

Activations Density 0.017%

words related to locations, events, and possibly names ending with 'esh'

No Comments

No Known Activations