INDEX

Explanations

phrases related to excessive quantities or intensities

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

ħĭ

-1.01

endants

-0.91

ĪĴ

-0.85

acus

-0.80

ramid

-0.76

saf

-0.76

geons

-0.76

ired

-0.74

raid

-0.73

stal

-0.71

POSITIVE LOGITS

 firepower

1.24

 attention

1.20

 money

1.13

 mileage

1.08

 variability

1.05

 emphasis

1.04

 misinformation

1.04

 information

1.04

 clout

1.01

 patience

1.01

Activations Density 1.122%

phrases related to excessive quantities or intensities

No Comments

No Known Activations