INDEX

Explanations

mentions of salaries or compensation-related terms

oai_token-act-pair · gpt-3.5-turbo

references to salary and compensation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ells

-0.81

Jess

-0.74

 Goodwin

-0.71

sonian

-0.71

 Ange

-0.71

 Sheen

-0.69

ennett

-0.68

 Ryder

-0.67

Jere

-0.67

 Edison

-0.66

POSITIVE LOGITS

 earners

1.09

 salary

0.97

 dues

0.90

 salaries

0.89

 income

0.86

 compensation

0.86

 earned

0.83

 sacrific

0.81

 payable

0.79

 deductions

0.77

Activations Density 0.023%

mentions of salaries or compensation-related terms

references to salary and compensation in various contexts

No Comments

No Known Activations