INDEX

Explanations

phrases related to defining or explaining concepts and characteristics

oai_token-act-pair · gpt-3.5-turbo

instances of the word "define" and its variations

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

ili

-0.79

itch

-0.71

ience

-0.69

rentice

-0.68

ilia

-0.67

athi

-0.66

rian

-0.66

paying

-0.65

riter

-0.63

 Remastered

-0.62

POSITIVE LOGITS

 defines

1.03

initions

0.96

 define

0.91

 defining

0.86

inition

0.84

 definitions

0.79

 defined

0.73

ãĥ¼ãĥĨãĤ£

0.72

=\"

0.71

FontSize

0.70

Activations Density 0.013%

phrases related to defining or explaining concepts and characteristics

instances of the word "define" and its variations

No Comments

No Known Activations