INDEX

Explanations

references to political figures and their actions.

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

 prest

-0.76

 ILCS

-0.71

ordial

-0.64

Balt

-0.63

 migr

-0.63

 largeDownload

-0.63

cend

-0.61

 Purg

-0.60

multipl

-0.60

 pilgrimage

-0.59

POSITIVE LOGITS

 inaction

1.00

 unfairly

0.86

 hypocrisy

0.80

 harshly

0.78

leaders

0.76

 failing

0.75

 coward

0.73

 shortcomings

0.73

 detractors

0.73

 critics

0.73

Activations Density 0.226%

references to political figures and their actions.

No Comments

No Known Activations