INDEX

Explanations

phrases related to controversy and its surrounding discussions

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

0:0.01

1:0.01

2:0.06

3:0.06

4:0.07

5:0.02

6:0.03

7:0.40

8:0.03

9:0.03

10:0.12

11:0.12

Negative Logits

empl

-1.52

anza

-1.49

eson

-1.48

 simulate

-1.47

itar

-1.45

 flexibility

-1.43

forts

-1.40

fter

-1.39

enary

-1.39

itia

-1.38

POSITIVE LOGITS

 accusations

1.54

 rumors

1.52

 controversies

1.51

 rumours

1.45

 tarn

1.43

 libel

1.43

 allegations

1.42

 sexism

1.40

 rumor

1.39

 suspicions

1.39

Activations Density 0.013%

phrases related to controversy and its surrounding discussions

No Comments

No Known Activations