INDEX

Explanations

occurrences of the word "that"

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

zos

-0.68

LD

-0.64

istries

-0.63

Member

-0.60

SB

-0.59

 Cancel

-0.58

ELY

-0.57

orously

-0.56

 Karn

-0.56

 Shelter

-0.55

POSITIVE LOGITS

 distingu

0.77

 prevailing

0.76

 imposed

0.76

 obser

0.73

 describ

0.72

 sket

0.72

 imagined

0.72

 estab

0.70

 pesky

0.70

 afforded

0.69

Activations Density 0.037%

occurrences of the word "that"

No Comments

No Known Activations