INDEX

Explanations

quantitative data points or statistics

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and reports

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

tone

-0.78

ctor

-0.71

andal

-0.68

engeance

-0.67

 mute

-0.64

 prank

-0.64

olit

-0.64

 innocence

-0.64

 Lovecraft

-0.64

Scene

-0.63

POSITIVE LOGITS

 Census

1.25

 Gallup

1.21

 census

1.19

 Nielsen

1.18

 Statistics

1.15

 OECD

1.14

Pew

1.09

 estimates

1.08

 statistics

1.06

Statistics

1.05

Activations Density 0.249%

quantitative data points or statistics

references to statistical data and reports

No Comments

No Known Activations