INDEX

Explanations

the article "a" followed by a word

oai_token-act-pair · gpt-3.5-turbo

the indefinite article 'a' used 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Twe

-0.71

 Tanz

-0.69

ank

-0.68

 rebounds

-0.65

ALP

-0.63

 adjourn

-0.63

 marks

-0.62

 sadd

-0.62

 Ãľ

-0.62

FSA

-0.61

POSITIVE LOGITS

ural

1.31

uras

1.30

ria

1.26

esthetic

1.25

ces

1.24

pron

1.24

ero

1.24

ld

1.19

lder

1.17

versions

1.17

Activations Density 0.081%

the article "a" followed by a word

the indefinite article 'a' used in various contexts

No Comments

No Known Activations