INDEX

Explanations

instances of the word "times" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

references to specific instances or occasions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĤ´

-0.93

æ©

-0.87

ãĤ¨ãĥ«

-0.86

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.77

è»

-0.77

ãĥīãĥ©ãĤ´ãĥ³

-0.73

ãĤ´ãĥ³

-0.72

ä½¿

-0.71

ãĥ´

-0.71

ãĥ¼ãĥĨãĤ£

-0.71

POSITIVE LOGITS

 lapse

0.83

 glimps

0.76

manship

0.72

 overlap

0.68

 moments

0.67

igmat

0.67

 forgiven

0.67

interrupted

0.66

 periods

0.65

 hesitation

0.65

Activations Density 0.126%

instances of the word "times" followed by a numerical value

references to specific instances or occasions

No Comments

No Known Activations