INDEX

Explanations

phrases related to variability and different forms

oai_token-act-pair · gpt-3.5-turbo

instances of phrases indicating variability or diversity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

¿

-0.88

ļ

-0.81

¤

-0.79

ª

-0.74

kee

-0.72

Ĥ

-0.71

ļéĨĴ

-0.71

£

-0.70

erton

-0.69

sburgh

-0.69

POSITIVE LOGITS

 depending

1.46

 varying

1.33

 differing

1.31

 ranging

1.27

 each

1.26

depending

1.19

each

1.11

 varies

1.09

different

1.07

 Each

1.05

Activations Density 0.296%

phrases related to variability and different forms

instances of phrases indicating variability or diversity

No Comments

No Known Activations