INDEX

Explanations

phrases related to comparing different options or scenarios

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

edia

-0.68

hai

-0.66

ounded

-0.66

ahime

-0.64

qus

-0.63

aughs

-0.62

ridor

-0.62

ItemTracker

-0.60

eln

-0.59

rition

-0.57

POSITIVE LOGITS

 imaginable

1.71

 except

1.43

 whatsoever

1.22

 conceivable

1.16

except

1.16

soever

1.10

 irrespective

1.04

 regardless

1.02

 thereafter

0.91

Except

0.82

Activations Density 1.913%

phrases related to comparing different options or scenarios

No Comments

No Known Activations