INDEX

Explanations

adjectives related to intensity or importance

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Veil

-0.69

CHAT

-0.64

ãĥĹ

-0.64

çĽ

-0.62

 Brief

-0.59

¸

-0.59

 guiActiveUn

-0.58

00200000

-0.58

Ô

-0.58

baum

-0.58

POSITIVE LOGITS

amus

0.86

idious

0.85

iated

0.69

 geographically

0.68

ifiable

0.68

 nodd

0.67

sided

0.64

 lately

0.64

athed

0.63

 athlet

0.63

Activations Density 0.808%

adjectives related to intensity or importance

No Comments

No Known Activations