INDEX

Explanations

phrases related to instructions or notes for readers

oai_token-act-pair · gpt-3.5-turbo

common phrases or prepositions indicating purpose or relation

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

 toget

-0.68

efully

-0.68

dev

-0.66

Â¯

-0.66

 reps

-0.65

daq

-0.64

 Laksh

-0.64

peat

-0.63

mone

-0.63

âĶĢ

-0.62

POSITIVE LOGITS

 Aging

0.99

 Characters

0.93

 Scene

0.89

 Bullets

0.88

 Coverage

0.88

 Ending

0.87

 Decay

0.86

 Ends

0.86

 Organizations

0.85

 Seasons

0.85

Activations Density 0.284%

phrases related to instructions or notes for readers

common phrases or prepositions indicating purpose or relation

No Comments

No Known Activations