INDEX

Explanations

phrases related to legal or law enforcement scenarios

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_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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 realise

-0.68

*)

-0.66

)'

-0.63

-)

-0.62

 Secondly

-0.60

 learnt

-0.59

 realised

-0.59

-0.58

Secondly

-0.57

Therefore

-0.57

POSITIVE LOGITS

å£

0.54

pees

0.54

 southwestern

0.51

 customized

0.50

 airborne

0.50

 billed

0.50

 funnel

0.50

 surfing

0.48

interstitial

0.48

"[

0.48

Activations Density 1.860%

phrases related to legal or law enforcement scenarios

No Comments

No Known Activations