INDEX

Explanations

phrases indicating a recurring pattern or series of events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

instead

-0.81

toc

-0.77

istan

-0.77

ATOR

-0.75

trl

-0.75

heit

-0.74

ifier

-0.74

ipedia

-0.74

Soc

-0.73

atown

-0.73

POSITIVE LOGITS

 incidents

1.38

 setbacks

1.38

 controversies

1.31

 scandals

1.21

 complaints

1.17

 delays

1.17

 failures

1.15

 successes

1.14

 leaks

1.14

 arrests

1.14

Activations Density 0.113%

phrases indicating a recurring pattern or series of events

No Comments

No Known Activations