INDEX

Explanations

phrases related to numerical values or ranges

oai_token-act-pair · gpt-3.5-turbo

phrases related to job types and employment statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ĸļ

-0.92

emonium

-0.82

 Tosh

-0.78

 swast

-0.74

 Malf

-0.73

 Zombies

-0.73

 clenched

-0.73

 Myster

-0.73

 Franz

-0.73

 Discord

-0.72

POSITIVE LOGITS

income

1.40

wage

1.16

employment

1.10

estate

1.10

health

1.05

government

1.04

advertising

1.04

education

1.02

service

1.00

state

0.98

Activations Density 0.210%

phrases related to numerical values or ranges

phrases related to job types and employment statistics

No Comments

No Known Activations