INDEX

Explanations

mentions or references related to the word "Independent"

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Ind" with high frequency related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

enegger

-0.84

utenberg

-0.75

avorite

-0.71

acter

-0.70

affer

-0.68

 damned

-0.67

ILA

-0.67

çķ

-0.66

vre

-0.66

 crest

-0.65

POSITIVE LOGITS

Ind

1.31

ependence

1.01

ebted

0.98

igenous

0.98

ividually

0.97

icative

0.95

irect

0.92

enture

0.90

epend

0.88

 Pacers

0.84

Activations Density 0.006%

mentions or references related to the word "Independent"

the presence of the word "Ind" with high frequency related to various contexts

No Comments

No Known Activations