INDEX

Explanations

references to well-paid roles or positions

oai_token-act-pair · gpt-3.5-turbo

terms related to job compensation and employment status

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

chat

-0.69

alter

-0.67

kill

-0.66

è£ħ

-0.65

codes

-0.64

clair

-0.64

Bridge

-0.62

FIN

-0.62

thur

-0.62

INTER

-0.61

POSITIVE LOGITS

 earners

0.88

 offspring

0.73

 individuals

0.73

 workers

0.73

 occupations

0.72

 enterprises

0.70

 employees

0.70

 jobs

0.69

 sectors

0.69

 professions

0.69

Activations Density 0.124%

references to well-paid roles or positions

terms related to job compensation and employment status

No Comments

No Known Activations