INDEX

Explanations

mentions of political campaigns and related activities, such as events, statements, and interviews

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 Compton

-0.76

sterdam

-0.67

isu

-0.66

 Kafka

-0.64

galitarian

-0.64

 warr

-0.64

obar

-0.62

ativity

-0.60

DEP

-0.60

^^^^

-0.60

POSITIVE LOGITS

cand

1.19

 campaigns

1.02

 candidate

1.02

 candidates

1.01

 campaign

1.00

 voters

1.00

Cand

0.98

 frontrunner

0.98

 Voters

0.94

INTON

0.93

Activations Density 1.741%

mentions of political campaigns and related activities, such as events, statements, and interviews

No Comments

No Known Activations