INDEX

Explanations

references to India

oai_token-act-pair · gpt-3.5-turbo

references to the term "Ind" or indicators of independence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

vre

-0.77

ework

-0.77

 snipers

-0.75

myra

-0.71

Blake

-0.71

 shards

-0.70

 scoop

-0.70

 claw

-0.68

 quarry

-0.68

eye

-0.68

POSITIVE LOGITS

Ind

3.84

Ind

2.41

IND

1.68

ind

1.43

ind

1.37

 Indo

1.32

 Indigo

1.32

 Indie

1.24

 indic

1.17

IND

1.15

Activations Density 0.033%

references to India

references to the term "Ind" or indicators of independence

No Comments

No Known Activations