INDEX

Explanations

phrases related to interpretation, understanding, and explanation

oai_token-act-pair · gpt-3.5-turbo

references to the concept of meaning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thumbnails

-0.77

 Thumbnails

-0.71

incinn

-0.71

oute

-0.71

emetery

-0.68

aliation

-0.67

artney

-0.64

arte

-0.63

 Frazier

-0.61

 Breed

-0.61

POSITIVE LOGITS

fully

1.24

lessness

1.13

fulness

1.02

ful

0.91

 meanings

0.90

notations

0.86

sworth

0.86

lessly

0.83

 Meaning

0.80

 meaning

0.79

Activations Density 0.017%

phrases related to interpretation, understanding, and explanation

references to the concept of meaning

No Comments

No Known Activations