INDEX

Explanations

statements related to criminal activities, investigations, and legal proceedings

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

 scenery

-0.75

 landscape

-0.73

 tremend

-0.72

ŃĶ

-0.70

 dynamically

-0.67

 gobl

-0.67

 everywhere

-0.67

 gorge

-0.67

 landscapes

-0.66

 defe

-0.65

POSITIVE LOGITS

 Additionally

1.32

 However

1.29

<|endoftext|>

1.20

 Previously

1.19

 Officials

1.19

 According

1.18

 Meanwhile

1.18

 Those

1.16

 Notably

1.16

↵

1.16

Activations Density 1.367%

statements related to criminal activities, investigations, and legal proceedings

No Comments

No Known Activations