INDEX

Explanations

phrases related to misinformation and public understanding of health care policies

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.07

3:0.10

4:0.06

5:0.08

6:0.10

7:0.07

8:0.09

9:0.07

10:0.08

11:0.09

Negative Logits

 spons

-1.66

ipedia

-1.62

tackle

-1.48

taboola

-1.47

inous

-1.47

 suspend

-1.44

dayName

-1.44

 prosec

-1.44

ratulations

-1.43

ntil

-1.40

POSITIVE LOGITS

)].

1.81

 Cros

1.70

 Folk

1.55

ICO

1.55

 Cassidy

1.53

swick

1.49

 Cain

1.48

 Mend

1.46

 裏�

1.45

 Kass

1.43

Activations Density 0.000%

phrases related to misinformation and public understanding of health care policies

No Comments

No Known Activations