INDEX

Explanations

names along with their job titles

oai_token-act-pair · gpt-3.5-turbo

names and titles related to political figures and institutions

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

$.

-0.64

 undet

-0.61

 detriment

-0.58

]."

-0.56

".[

-0.55

EStreamFrame

-0.54

 therein

-0.53

ãģĻ

-0.52

 vulner

-0.52

").

-0.52

POSITIVE LOGITS

 meanwhile

0.97

 echoed

0.77

 reacted

0.70

 congratulated

0.64

 commented

0.63

 spokesman

0.62

 welcomed

0.62

 applauded

0.62

 countered

0.62

 responded

0.61

Activations Density 1.179%

names along with their job titles

names and titles related to political figures and institutions

No Comments

No Known Activations