INDEX

Explanations

phrases related to conflicts and resolutions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consequences or outcomes involving significant implications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 earthqu

-0.71

 unbeliev

-0.66

erenn

-0.61

bucks

-0.57

 subur

-0.56

 Fold

-0.55

 Lans

-0.54

asma

-0.54

schild

-0.54

sie

-0.53

POSITIVE LOGITS

 therefore

1.06

 consequently

1.03

".

1.02

 "âĢ¦

0.99

".[

0.94

 accordingly

0.93

 "...

0.91

 thereafter

0.91

"[

0.91

 deserved

0.90

Activations Density 0.718%

phrases related to conflicts and resolutions

phrases indicating consequences or outcomes involving significant implications

No Comments

No Known Activations