INDEX

Explanations

pronouns and related phrases

oai_token-act-pair · gpt-3.5-turbo

pronouns and their usage in sentences

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

Reviewer

-0.62

 Flavoring

-0.60

 recent

-0.60

%%%%

-0.55

 Have

-0.54

paren

-0.53

umph

-0.53

 hiatus

-0.53

UGH

-0.52

 Recently

-0.52

POSITIVE LOGITS

 depended

1.52

 mattered

1.51

 tended

1.44

 interacted

1.33

 resembled

1.30

 flowed

1.30

 risked

1.27

 differed

1.27

 wore

1.24

 interfered

1.23

Activations Density 0.661%

pronouns and related phrases

pronouns and their usage in sentences

No Comments

No Known Activations