INDEX

Explanations

positive emotional expressions

oai_token-act-pair · gpt-3.5-turbo

expressions conveying emotions such as happiness, gladness, and relief

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

%,

-0.74

`,

-0.72

Ø

-0.68

\\\\

-0.68

\'

-0.68

?,

-0.66

*)

-0.65

,,

-0.65

 msec

-0.64

acia

-0.64

POSITIVE LOGITS

 marketers

0.78

 Capcom

0.77

to

0.76

 Whedon

0.74

we

0.73

 Paramount

0.73

 Marvel

0.73

 ESPN

0.72

 Sony

0.71

 everyone

0.71

Activations Density 0.442%

positive emotional expressions

expressions conveying emotions such as happiness, gladness, and relief

No Comments

No Known Activations