INDEX

Explanations

proper nouns related to movie titles and historical events

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ãĥ¯ãĥ³

-0.68

ãĥ¼ãĥĨãĤ£

-0.67

 spirited

-0.66

ħĭ

-0.64

éĹĺ

-0.63

 compensated

-0.61

 shattered

-0.60

 Shogun

-0.60

 stoked

-0.60

PDATE

-0.59

POSITIVE LOGITS

ayers

1.13

ounge

1.10

oyd

1.09

opez

1.08

ateral

1.07

ibraries

1.06

eston

1.05

ifestyle

1.02

ocated

1.02

yrics

1.00

Activations Density 0.047%

proper nouns related to movie titles and historical events

No Comments

No Known Activations