INDEX

Explanations

terms and phrases related to accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

yip

-0.82

apore

-0.79

ijn

-0.75

lyn

-0.73

colo

-0.69

ãĥĩãĤ£

-0.68

ker

-0.66

 Alic

-0.66

tein

-0.65

ijk

-0.64

POSITIVE LOGITS

 accountable

0.97

rity

0.84

 Accountability

0.78

 deeds

0.76

Reporting

0.75

 accountability

0.75

 wrongdoing

0.74

 criminally

0.71

ible

0.71

abilities

0.70

Activations Density 0.019%

terms and phrases related to accountability

No Comments

No Known Activations