INDEX

Explanations

deadlines and time-related phrases

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_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

ector

-0.88

ateur

-0.86

stown

-0.81

agate

-0.80

oles

-0.75

âĵĺ

-0.73

rosse

-0.72

quer

-0.71

port

-0.70

otto

-0.70

POSITIVE LOGITS

 deadline

1.13

 deadlines

1.11

 imposed

0.85

 looms

0.79

 schedule

0.78

 clearance

0.77

 timeframe

0.75

 expired

0.74

 timer

0.73

 looming

0.73

Activations Density 0.024%

deadlines and time-related phrases

No Comments

No Known Activations