INDEX

Explanations

technical terms related to government policies and procedures

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 bere

-0.63

bourg

-0.61

iture

-0.59

 divest

-0.58

istar

-0.57

 academic

-0.56

 fulfillment

-0.56

 kidnap

-0.55

 WATCHED

-0.55

swick

-0.54

POSITIVE LOGITS

0.94

0.92

Cs

0.90

0.87

Bs

0.86

0.83

shaped

0.83

0.81

0.80

0.79

Activations Density 1.211%

technical terms related to government policies and procedures

No Comments

No Known Activations