INDEX

Explanations

terms related to technology features

oai_token-act-pair · gpt-3.5-turbo

references to specific features and functionalities

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

sis

-0.83

oner

-0.71

azar

-0.71

cffffcc

-0.69

utral

-0.68

aline

-0.67

itude

-0.66

zzi

-0.66

apy

-0.65

Ã§a

-0.65

POSITIVE LOGITS

 features

1.06

Features

1.02

Feature

1.02

 Features

0.99

afety

0.95

 prominently

0.93

features

0.93

 Include

0.85

hips

0.83

feature

0.82

Activations Density 0.020%

terms related to technology features

references to specific features and functionalities

No Comments

No Known Activations