INDEX

Explanations

words related to people's names

oai_token-act-pair · gpt-3.5-turbo

the presence of a specific name or term repeatedly mentioned 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

GGGGGGGG

-0.72

 Bucks

-0.69

 Yemeni

-0.63

 Somalia

-0.61

é¾įå

-0.60

 Belgium

-0.60

 Ethiopia

-0.60

 Axis

-0.59

Äĩ

-0.58

 Macedonia

-0.58

POSITIVE LOGITS

apeake

1.22

terday

1.19

creen

1.08

hire

0.94

chool

0.92

ema

0.87

gemony

0.87

hirt

0.87

worth

0.85

chel

0.84

Activations Density 0.014%

words related to people's names

the presence of a specific name or term repeatedly mentioned in various contexts

No Comments

No Known Activations