INDEX

Explanations

proper nouns and names mentioned in the text.

oai_token-act-pair · gpt-3.5-turbo

specific names or identifiers related to individuals or entities

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

 therm

-0.83

Tyr

-0.80

 Bron

-0.80

Ther

-0.79

Bet

-0.79

 predicate

-0.79

æ³

-0.78

DPR

-0.73

 Playstation

-0.73

 Monster

-0.72

POSITIVE LOGITS

ang

1.37

Sing

1.31

ANG

1.31

ong

1.31

Ung

1.24

ongs

1.23

ung

1.17

sung

1.17

 Wong

1.16

angs

1.16

Activations Density 0.251%

proper nouns and names mentioned in the text.

specific names or identifiers related to individuals or entities

No Comments

No Known Activations