INDEX

Explanations

people working in service positions, such as attendants, clerks, waiters, and waitresses

oai_token-act-pair · gpt-3.5-turbo

references to service roles or occupations in various settings

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

 Flavoring

-0.82

çīĪ

-0.71

theless

-0.68

 Marketable

-0.68

orsche

-0.68

ationally

-0.68

IJ

-0.68

itars

-0.66

 Born

-0.65

bsp

-0.63

POSITIVE LOGITS

esses

1.10

 attendants

1.03

 attendant

0.94

ess

0.91

 supervisor

0.83

 waitress

0.83

 clerk

0.83

 cafeteria

0.82

 maid

0.81

 boun

0.78

Activations Density 0.188%

people working in service positions, such as attendants, clerks, waiters, and waitresses

references to service roles or occupations in various settings

No Comments

No Known Activations