INDEX

Explanations

words with the suffix "-en"

oai_token-act-pair · gpt-3.5-turbo

a variety of proper nouns and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Carib

-0.90

 Boyle

-0.80

Bog

-0.77

tyr

-0.77

 Bohem

-0.75

 Rabbit

-0.75

 Bolivia

-0.75

MGM

-0.74

rag

-0.74

 Cycl

-0.74

POSITIVE LOGITS

en

1.79

EN

1.61

ename

1.42

enf

1.41

ens

1.39

ena

1.35

enh

1.33

eni

1.31

eng

1.28

eny

1.28

Activations Density 0.141%

words with the suffix "-en"

a variety of proper nouns and technical terms

No Comments

No Known Activations