INDEX

Explanations

indicators of governmental operations or legal documentation related to security and intelligence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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¬

-0.67

é¾įå¥ĳå£«

-0.65

esp

-0.62

ModLoader

-0.60

 Scorp

-0.60

Jiu

-0.59

ãĥŃ

-0.58

 mafia

-0.58

 Geneva

-0.57

çĭ

-0.57

POSITIVE LOGITS

intendent

0.90

andise

0.89

urer

0.86

ature

0.83

icut

0.82

ussion

0.82

aign

0.81

ior

0.81

nant

0.80

itely

0.79

Activations Density 0.020%

indicators of governmental operations or legal documentation related to security and intelligence

No Comments

No Known Activations