INDEX

Explanations

proper nouns and names, particularly related to news and politics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Els

-0.74

Load

-0.72

oard

-0.66

 Agric

-0.62

ories

-0.61

Ire

-0.61

 Dominion

-0.60

Wem

-0.60

Georg

-0.60

Region

-0.59

POSITIVE LOGITS

Jr

1.39

Sr

1.11

III

1.06

aka

0.93

 famously

0.93

agher

0.89

Jr

0.86

's

0.86

 himself

0.82

ovich

0.82

Activations Density 2.050%

proper nouns and names, particularly related to news and politics

No Comments

No Known Activations