INDEX

Explanations

mentions of employment and job-related terms

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

Oo

-0.79

 Flavoring

-0.74

 Revision

-0.72

 Bulg

-0.69

Interstitial

-0.69

 Amph

-0.65

 Jamaica

-0.65

orp

-0.61

 sidx

-0.60

 Blast

-0.60

POSITIVE LOGITS

anooga

0.83

job

0.81

 postings

0.81

jobs

0.81

Builder

0.80

days

0.80

 jobs

0.80

uilt

0.76

 unemploy

0.74

 seeker

0.74

Activations Density 0.416%

mentions of employment and job-related terms

No Comments

No Known Activations