INDEX

Explanations

expressions indicating levels of uncertainty or caution

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

0:0.06

1:0.02

2:0.05

3:0.34

4:0.03

5:0.04

6:0.01

7:0.04

8:0.02

9:0.01

10:0.30

11:0.02

Negative Logits

 heroine

-1.87

 WRITE

-1.87

 campaigner

-1.82

 NEWS

-1.79

 Chronicles

-1.77

 protector

-1.77

VIDEO

-1.76

 extensively

-1.72

 hoax

-1.71

 gripping

-1.71

POSITIVE LOGITS

 expense

3.00

 level

2.86

 intervals

2.85

 heights

2.48

 discretion

2.45

 pinnacle

2.42

minimum

2.36

 whim

2.36

peed

2.34

 vantage

2.34

Activations Density 0.325%

expressions indicating levels of uncertainty or caution

No Comments

No Known Activations