INDEX

Explanations

positive words and phrases, possibly related to favorable outcomes or aspects

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

puter

-0.90

ĸļ

-0.87

hid

-0.87

ometimes

-0.84

plain

-0.81

ptin

-0.80

appings

-0.79

pread

-0.78

alian

-0.78

alus

-0.77

POSITIVE LOGITS

 reinforcement

1.09

 outlook

1.06

 feedback

1.06

 attitude

1.02

vib

0.99

 outcome

0.95

 appraisal

0.94

 affirmation

0.89

 affirm

0.87

 gearing

0.86

Activations Density 0.809%

positive words and phrases, possibly related to favorable outcomes or aspects

No Comments

No Known Activations