INDEX

Explanations

words related to comparisons and examples

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce examples or clarifications

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

\\\\\\\\

-0.74

ESA

-0.70

mone

-0.70

Ú

-0.69

ZI

-0.67

Param

-0.63

COMPLE

-0.63

Mach

-0.63

MAP

-0.62

âĢİ

-0.61

POSITIVE LOGITS

older

0.68

 swayed

0.67

 differed

0.64

 weren

0.63

 aren

0.61

 executed

0.60

 alike

0.59

pired

0.59

 were

0.59

 exchanged

0.58

Activations Density 0.500%

words related to comparisons and examples

phrases that introduce examples or clarifications

No Comments

No Known Activations