INDEX

Explanations

phrases related to positions or stances on various topics

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "position" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rosso

-0.81

ebook

-0.81

displayText

-0.76

ãĥ¼ãĥĨãĤ£

-0.71

vous

-0.69

issance

-0.68

Interstitial

-0.68

STON

-0.67

ilee

-0.65

 Bagg

-0.63

POSITIVE LOGITS

 positions

1.23

 position

1.18

holders

1.10

holder

1.01

 holders

0.88

 holder

0.86

quo

0.84

 orientation

0.82

ession

0.80

 stances

0.79

Activations Density 0.032%

phrases related to positions or stances on various topics

occurrences of the term "position" in various contexts

No Comments

No Known Activations