INDEX

Explanations

words related to incorporating, integrating, or injecting elements into something

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

Ĥİ

-0.67

runner

-0.65

sem

-0.63

Reply

-0.61

 Correspond

-0.60

jobs

-0.59

efer

-0.59

cale

-0.59

ARB

-0.58

 Citiz

-0.58

POSITIVE LOGITS

 into

1.41

 INTO

1.27

into

1.27

 Into

1.25

 onto

1.08

tion

0.89

icut

0.78

antly

0.77

ively

0.76

urated

0.74

Activations Density 1.169%

words related to incorporating, integrating, or injecting elements into something

No Comments

No Known Activations