INDEX

Explanations

names of individuals or specific entities mentioned in the text

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

angers

-0.80

keyes

-0.79

acea

-0.76

aceous

-0.72

keye

-0.71

spective

-0.70

aido

-0.70

alez

-0.69

orders

-0.69

lando

-0.68

POSITIVE LOGITS

leon

1.10

lled

0.95

eh

0.89

0.87

lla

0.84

Ã±a

0.84

llan

0.81

ez

0.80

lling

0.78

xual

0.78

Activations Density 0.024%

names of individuals or specific entities mentioned in the text

No Comments

No Known Activations