INDEX

Explanations

mentions of conflict and military activities

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

payer

-0.73

NAD

-0.72

 Canal

-0.71

 Pension

-0.70

 nutrit

-0.70

 Quality

-0.69

NH

-0.68

é¾įå

-0.68

 cushion

-0.68

ilts

-0.67

POSITIVE LOGITS

 infiltr

1.27

 invading

1.25

 attacking

1.17

 menacing

1.17

 threatening

1.16

 attacks

1.14

 attack

1.14

 lurking

1.13

 infiltration

1.11

 stalking

1.11

Activations Density 3.466%

mentions of conflict and military activities

No Comments

No Known Activations