INDEX

Explanations

phrases related to a repetition of actions or roles

oai_token-act-pair · gpt-3.5-turbo

variations of the word "reprising."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rid

-0.73

ihu

-0.73

emetery

-0.71

¾

-0.70

odynamic

-0.69

oat

-0.69

Grid

-0.68

 livest

-0.68

ox

-0.67

utsche

-0.67

POSITIVE LOGITS

prising

1.10

prise

1.02

xtap

0.96

ãĤ©

0.93

prises

0.84

ãĥĻ

0.80

 Mechdragon

0.79

 cheers

0.74

ilus

0.71

pic

0.68

Activations Density 0.025%

phrases related to a repetition of actions or roles

variations of the word "reprising."

No Comments

No Known Activations