INDEX

Explanations

phrases related to legal actions and investigations

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nothing

-0.83

ESE

-0.80

NER

-0.72

bas

-0.71

urden

-0.70

instead

-0.69

thus

-0.69

ola

-0.69

anything

-0.69

IAS

-0.69

POSITIVE LOGITS

 hundred

1.40

 sclerosis

1.25

 dozen

1.24

 thousand

1.22

 iterations

1.18

 incarn

1.11

 occasions

1.06

 layers

1.06

 kinds

1.06

 facets

1.05

Activations Density 0.258%

phrases related to legal actions and investigations

No Comments

No Known Activations