INDEX

Explanations

mentions of wages in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to wages and discussions surrounding them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

DEP

-0.76

OPS

-0.73

ocl

-0.68

ergy

-0.65

\/\/

-0.65

Jub

-0.63

ctica

-0.62

olog

-0.61

TIT

-0.61

 Greene

-0.61

POSITIVE LOGITS

 earners

1.07

 wages

1.03

wage

0.92

 wage

0.87

 Wage

0.83

 payable

0.81

chwitz

0.79

($)

0.79

 labou

0.79

aving

0.77

Activations Density 0.007%

mentions of wages in various contexts

references to wages and discussions surrounding them

No Comments

No Known Activations