INDEX

Explanations

words related to political systems and policies

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

queue

-0.85

 consulted

-0.72

ichen

-0.71

jan

-0.68

BILL

-0.67

ade

-0.67

quer

-0.67

 UPDATE

-0.67

amazon

-0.66

 Provided

-0.65

POSITIVE LOGITS

 displeasure

1.09

 individuality

1.08

 seriousness

1.05

 discontent

1.04

 masculinity

1.04

 greatness

1.03

 humanity

1.03

 sentiments

0.98

 dissatisfaction

0.98

 sincerity

0.97

Activations Density 2.774%

words related to political systems and policies

No Comments

No Known Activations