INDEX

Explanations

words related to a specific person's name

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or names associated with particular arguments or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

gling

-0.80

 HELL

-0.69

model

-0.63

 Privacy

-0.63

 reconc

-0.62

lining

-0.62

regon

-0.60

 cryptic

-0.59

 Spartans

-0.59

 captcha

-0.58

POSITIVE LOGITS

aza

1.37

ire

1.01

Ã«

0.91

ifa

0.88

eed

0.87

elta

0.84

hea

0.84

ption

0.80

asca

0.80

heim

0.79

Activations Density 0.009%

words related to a specific person's name

references to specific individuals or names associated with particular arguments or subjects

No Comments

No Known Activations