INDEX

Explanations

personal details about individuals

oai_token-act-pair · gpt-3.5-turbo

the pronoun "who" as it appears 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Pg

-0.71

ENDED

-0.63

 VIDEOS

-0.63

ILLE

-0.62

estyles

-0.58

APD

-0.58

PLA

-0.57

Temperature

-0.55

Operation

-0.55

 antioxid

-0.53

POSITIVE LOGITS

who

2.78

who

2.71

 whom

2.44

 whose

2.00

whose

1.90

Who

1.69

Who

1.68

WHO

1.39

WHO

1.36

omever

0.91

Activations Density 0.164%

personal details about individuals

the pronoun "who" as it appears in various contexts

No Comments

No Known Activations