INDEX

Explanations

instances of the word "into."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

æ©Ł

-0.80

ice

-0.71

aires

-0.71

anooga

-0.68

asma

-0.68

cause

-0.64

 distur

-0.64

ARI

-0.63

gang

-0.63

ailable

-0.62

POSITIVE LOGITS

 adulthood

1.12

 adolescence

0.75

 captivity

0.73

 existence

0.70

 gestation

0.69

 retirement

0.69

 Reign

0.68

 repayment

0.67

 renovations

0.65

 puberty

0.65

Activations Density 0.015%

instances of the word "into."

No Comments

No Known Activations