INDEX

Explanations

mentions of public figures and political 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

Cause

-0.71

ords

-0.66

direction

-0.66

icum

-0.65

nect

-0.64

ãĤ¼ãĤ¦ãĤ¹

-0.63

"]=>

-0.62

beit

-0.62

uld

-0.62

lled

-0.62

POSITIVE LOGITS

 alike

1.43

 extraord

1.23

 respectively

1.17

 advocate

0.85

 educator

0.73

 Richard

0.70

 enthusiast

0.67

Ann

0.65

 activist

0.64

 specializing

0.64

Activations Density 0.110%

mentions of public figures and political events

No Comments

No Known Activations