INDEX

Explanations

mentions of names, titles, and affiliations in news articles

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

Ö¼

-0.67

 Seym

-0.66

hovah

-0.66

sburgh

-0.65

ENC

-0.61

ledged

-0.58

âĢ¢âĢ¢

-0.57

 reluct

-0.57

 plur

-0.56

 WARNING

-0.56

POSITIVE LOGITS

ning

1.55

igans

1.37

ned

1.36

onymous

1.26

ews

1.19

nery

1.18

tern

1.15

thal

1.11

alyst

1.10

zo

1.10

Activations Density 2.676%

mentions of names, titles, and affiliations in news articles

No Comments

No Known Activations