INDEX

Explanations

the use of the word "only."

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

0:0.08

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.10

Negative Logits

Columb

-3.20

Iowa

-3.07

 Sioux

-3.00

Minnesota

-2.95

Arizona

-2.94

Socket

-2.87

 Spartan

-2.85

eka

-2.79

CBS

-2.77

inventoryQuantity

-2.65

POSITIVE LOGITS

 showc

2.98

 journals

2.82

 editors

2.62

 resolutions

2.58

 formulas

2.54

 counting

2.52

 publish

2.46

 publications

2.40

 loopholes

2.40

 lett

2.40

Activations Density 0.000%

the use of the word "only."

No Comments

No Known Activations