INDEX

Explanations

specific phrases related to completion or entirety

oai_token-act-pair · gpt-3.5-turbo

references to completeness and thoroughness 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 @ 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

 nearby

-0.62

ammers

-0.62

 brightly

-0.62

 spat

-0.61

jan

-0.60

 plac

-0.59

 lull

-0.58

chance

-0.57

 pige

-0.57

Myr

-0.57

POSITIVE LOGITS

ledged

0.79

isites

0.73

ACTION

0.72

ãĤ¼ãĤ¦ãĤ¹

0.72

ngth

0.68

Initialized

0.68

 except

0.67

opathic

0.67

DragonMagazine

0.66

keye

0.65

Activations Density 0.272%

specific phrases related to completion or entirety

references to completeness and thoroughness in various contexts

No Comments

No Known Activations