INDEX

Explanations

references to characters named Tyr or themes related to tyranny

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

âĸ¬âĸ¬

-0.73

BOOK

-0.70

manship

-0.68

 congr

-0.67

PRESS

-0.64

FORM

-0.64

PUT

-0.63

Ou

-0.63

 Papua

-0.61

ãģ®éŃĶ

-0.60

POSITIVE LOGITS

anny

1.32

rell

1.14

rible

1.03

anus

1.00

acious

0.93

anic

0.90

rod

0.87

onic

0.85

ant

0.83

ion

0.82

Activations Density 0.004%

references to characters named Tyr or themes related to tyranny

No Comments

No Known Activations