INDEX

Explanations

emphatic phrases indicating important or impactful events or situations

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

none

-0.76

friends

-0.75

KER

-0.71

cs

-0.68

chairs

-0.67

acons

-0.64

Dr

-0.64

rants

-0.63

killers

-0.61

ics

-0.61

POSITIVE LOGITS

hearted

1.04

 ordeal

1.04

 thing

1.02

heartedly

1.01

 spectrum

0.98

gam

0.96

 globe

0.96

 affair

0.88

 ecosystem

0.88

 continent

0.86

Activations Density 0.156%

emphatic phrases indicating important or impactful events or situations

No Comments

No Known Activations