INDEX

Explanations

mentions of pronouns related to individuals and their actions or states

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

é¾įå¥ĳå£«

-0.64

 Vanity

-0.64

 Innocent

-0.62

 Observer

-0.61

 Yesterday

-0.60

NK

-0.60

 Kirin

-0.59

NP

-0.59

 Oriental

-0.59

Nin

-0.58

POSITIVE LOGITS

'll

1.11

'd

1.08

 proceeded

1.06

 reverted

1.02

 withdrew

1.00

 recons

1.00

 resumed

0.99

 realized

0.98

 retreated

0.97

 encount

0.96

Activations Density 0.144%

mentions of pronouns related to individuals and their actions or states

No Comments

No Known Activations