INDEX

Explanations

references to systemic issues related to accountability, transparency, and corruption

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Champ

-0.77

çīĪ

-0.73

EVA

-0.73

USB

-0.70

ALSE

-0.69

NOW

-0.68

none

-0.66

ATHER

-0.65

BUS

-0.65

etsk

-0.65

POSITIVE LOGITS

 lieu

1.17

 relation

1.14

effic

1.13

 favor

1.13

efficiency

1.08

 regards

1.03

 academia

1.00

 favour

0.99

 society

0.97

 accordance

0.94

Activations Density 0.133%

references to systemic issues related to accountability, transparency, and corruption

No Comments

No Known Activations