INDEX

Explanations

the name "Be" at varying degrees of relevance

oai_token-act-pair · gpt-3.5-turbo

the letter combination "Be" in various contexts

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

 firsthand

-0.73

 totality

-0.68

 glide

-0.63

 resonance

-0.63

ĸļ

-0.62

 drift

-0.62

 scope

-0.61

ilver

-0.61

 Comet

-0.61

 indictment

-0.61

POSITIVE LOGITS

arers

1.21

yond

1.20

hemoth

1.19

aum

1.14

arer

1.14

ech

1.12

acons

1.11

auc

1.03

aker

1.02

ards

1.02

Activations Density 0.028%

the name "Be" at varying degrees of relevance

the letter combination "Be" in various contexts

No Comments

No Known Activations