INDEX

Explanations

phrases related to locations, destinations, and availability

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

advertisement

-0.69

achev

-0.67

 Hacker

-0.65

iasco

-0.64

ACY

-0.62

itsu

-0.62

 Malone

-0.62

 ..............

-0.61

naires

-0.61

SB

-0.61

POSITIVE LOGITS

 resides

0.91

 resided

0.91

 reside

0.91

 congreg

0.82

 intersect

0.82

 geographically

0.79

 holiest

0.79

ezvous

0.78

 weakest

0.75

 belong

0.75

Activations Density 1.334%

phrases related to locations, destinations, and availability

No Comments

No Known Activations