INDEX

Explanations

words related to advertisements and marketing strategies

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

claw

-0.74

 Templar

-0.72

Jr

-0.69

borg

-0.67

 Carbuncle

-0.66

 TAMADRA

-0.65

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.65

essional

-0.64

lihood

-0.64

iciary

-0.64

POSITIVE LOGITS

vertising

1.02

 campaigns

1.01

 advertising

0.94

verts

0.92

 banners

0.88

 blitz

0.88

 slogan

0.85

 billboards

0.84

 Advertising

0.83

 campaign

0.81

Activations Density 2.779%

words related to advertisements and marketing strategies

No Comments

No Known Activations