INDEX

Explanations

phrases related to a particular entity or character named "Qu."

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

AGES

-0.69

 deed

-0.68

 heart

-0.68

HAEL

-0.67

 contrast

-0.67

 intens

-0.66

 intensity

-0.65

 conditioning

-0.63

 Lyme

-0.63

 Beir

-0.63

POSITIVE LOGITS

arantine

1.30

artz

1.09

ipped

1.09

inoa

1.09

oted

1.09

arie

1.08

icks

1.08

ests

1.04

irk

1.03

oting

1.03

Activations Density 0.018%

phrases related to a particular entity or character named "Qu."

No Comments

No Known Activations