INDEX

Explanations

phrases related to legal actions or government involvement

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

uality

-0.96

empl

-0.77

ppa

-0.75

redits

-0.75

heimer

-0.72

NN

-0.69

chrome

-0.69

 largeDownload

-0.68

bia

-0.68

iza

-0.68

POSITIVE LOGITS

 virtue

1.21

products

0.88

laws

0.87

 passers

0.85

 STATS

0.83

 extremists

0.81

 locals

0.80

 outsiders

0.80

 professionals

0.77

 successive

0.77

Activations Density 0.689%

phrases related to legal actions or government involvement

No Comments

No Known Activations