INDEX

Explanations

strong emotional language and criticism in political contexts

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

ocument

-0.76

scope

-0.74

ICLE

-0.70

aea

-0.70

rh

-0.69

ometime

-0.69

emetery

-0.68

OTE

-0.68

minster

-0.68

matic

-0.67

POSITIVE LOGITS

 critics

1.03

 commenters

0.94

 critic

0.88

 mockery

0.88

 hypocrisy

0.87

 bullies

0.84

 detractors

0.84

 merciless

0.84

 accusing

0.83

 harshly

0.83

Activations Density 1.185%

strong emotional language and criticism in political contexts

No Comments

No Known Activations