INDEX

Explanations

words related to physical or cyber attacks

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ©

-0.81

dit

-0.68

isphere

-0.64

YC

-0.63

mbuds

-0.60

zl

-0.59

inders

-0.58

 Alive

-0.58

 Solitaire

-0.58

 Genie

-0.57

POSITIVE LOGITS

 against

1.01

 attacks

0.90

iveness

0.89

 attack

0.86

attack

0.84

 vector

0.84

CVE

0.81

 waged

0.79

 inflicting

0.78

Attack

0.77

Activations Density 0.705%

words related to physical or cyber attacks

No Comments

No Known Activations