INDEX

Explanations

phrases indicating future events or expectations

oai_token-act-pair · gpt-4o-mini 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

advant

-0.70

quartered

-0.67

 guiActiveUnfocused

-0.65

Engineers

-0.64

 allegedly

-0.64

NAS

-0.63

eworthy

-0.63

atial

-0.61

 Operating

-0.60

 patriarch

-0.60

POSITIVE LOGITS

 tomorrow

0.82

 ASAP

0.74

 plenty

0.73

 gladly

0.72

ya

0.72

 soon

0.72

eeee

0.72

 thee

0.71

 updates

0.70

 Tune

0.69

Activations Density 0.210%

phrases indicating future events or expectations

No Comments

No Known Activations