INDEX

Explanations

information related to cancellations and disruptions in various situations, such as events, flights, and programs

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

ebus

-0.69

 dens

-0.66

aez

-0.62

transform

-0.62

rious

-0.61

entimes

-0.60

ieth

-0.59

cycl

-0.58

inka

-0.58

 imperfect

-0.57

POSITIVE LOGITS

 altogether

1.11

 indefinitely

1.02

 abruptly

1.01

 unres

0.87

 disbelief

0.86

 entirely

0.85

 citing

0.83

 outright

0.81

 voluntarily

0.81

 prematurely

0.78

Activations Density 0.896%

information related to cancellations and disruptions in various situations, such as events, flights, and programs

No Comments

No Known Activations