INDEX

Explanations

phrases and words related to dates and events

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.01

2:0.03

3:0.07

4:0.02

5:0.07

6:0.02

7:0.08

8:0.02

9:0.04

10:0.07

11:0.48

Negative Logits

.):

-3.35

:]

-3.27

.:

-2.89

 eleph

-2.70

):

-2.60

%%

-2.56

viz

-2.55

��

-2.45

 +---

-2.44

})

-2.42

POSITIVE LOGITS

,...

2.78

SPONSORED

2.73

...

2.59

,[

2.51

BuyableInstoreAndOnline

2.30

 OPEC

2.26

Interstitial

2.19

 Congressional

2.12

taboola

2.11

 Plaint

2.08

Activations Density 0.008%

phrases and words related to dates and events

No Comments

No Known Activations