INDEX

Explanations

phrases related to courses or programs

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize common expressions or references in discussions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Discuss

-0.81

catentry

-0.73

è¦ļéĨĴ

-0.71

MpServer

-0.65

OWN

-0.64

SourceFile

-0.63

Dialog

-0.63

DOWN

-0.62

Reviewed

-0.62

panel

-0.61

POSITIVE LOGITS

chio

0.67

tsky

0.67

ividual

0.66

 Eliot

0.65

 assumes

0.65

ongs

0.65

 THERE

0.64

 Tycoon

0.63

icion

0.62

;;;;;;;;

0.62

Activations Density 0.073%

phrases related to courses or programs

phrases that emphasize common expressions or references in discussions

No Comments

No Known Activations