INDEX

Explanations

terms related to specific Unicode characters and symbols

oai_token-act-pair · gpt-3.5-turbo

special characters or unusual symbols

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

etheless

-1.05

 contrace

-0.90

 agre

-0.86

srf

-0.86

ebus

-0.86

espie

-0.83

anol

-0.81

orno

-0.80

abase

-0.79

quished

-0.78

POSITIVE LOGITS

ãĤ³

1.32

é¾į

1.31

å

1.30

çĶ°

1.29

ãĤ«

1.29

åº

1.26

ãĤ

1.26

åį

1.25

å¸

1.24

åĪ

1.23

Activations Density 0.066%

terms related to specific Unicode characters and symbols

special characters or unusual symbols

No Comments

No Known Activations