INDEX

Explanations

personal pronouns followed by reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

personal pronouns and their usage in context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orting

-0.61

 Eleven

-0.60

ntil

-0.60

bats

-0.59

orted

-0.57

 Dayton

-0.57

 provisional

-0.56

gradation

-0.56

 Towards

-0.55

CLASSIFIED

-0.55

POSITIVE LOGITS

 feared

1.18

 knew

1.14

 believe

1.08

 felt

1.08

 smelled

1.04

 wanted

1.03

 lacked

1.02

 sensed

1.01

 KNOW

1.00

 believed

1.00

Activations Density 0.190%

personal pronouns followed by reasons or explanations

personal pronouns and their usage in context

No Comments

No Known Activations