INDEX

Explanations

mentions of large entities or institutions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

manship

-0.79

Dialogue

-0.69

chron

-0.68

cia

-0.68

yrinth

-0.68

 Emin

-0.67

qi

-0.67

istry

-0.65

CF

-0.65

gemony

-0.65

POSITIVE LOGITS

oted

1.15

 chunk

1.05

gest

1.03

 scale

1.01

 chunks

0.98

 swath

0.92

 intestine

0.92

 swat

0.90

 quantities

0.87

 sized

0.85

Activations Density 1.377%

mentions of large entities or institutions

No Comments

No Known Activations