INDEX

Explanations

references to salary-related terms

oai_token-act-pair · gpt-3.5-turbo

references to salary and compensation in employment contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

ells

-0.77

 Goodwin

-0.72

 Twist

-0.69

Interstitial

-0.68

Jess

-0.67

sonian

-0.67

 Glad

-0.67

 Edison

-0.66

ery

-0.65

POSITIVE LOGITS

 earners

1.07

 salary

0.99

 dues

0.91

 salaries

0.89

 compensation

0.84

 income

0.80

 wages

0.78

 sacrific

0.78

 earned

0.76

 payable

0.76

Activations Density 0.018%

references to salary-related terms

references to salary and compensation in employment contexts

No Comments

No Known Activations