INDEX

Explanations

the word "reform" and related concepts associated with governance and social change

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.02

2:0.07

3:0.18

4:0.01

5:0.03

6:0.08

7:0.21

8:0.06

9:0.07

10:0.07

11:0.13

Negative Logits

owitz

-1.25

eele

-1.16

thing

-1.16

ottesville

-1.16

ahl

-1.12

ubi

-1.11

atar

-1.08

nis

-1.08

blank

-1.07

zers

-1.02

POSITIVE LOGITS

 Recon

1.10

 reformed

1.09

 constitution

1.06

 tackling

1.04

ivism

1.02

 reforming

1.01

arta

1.01

catentry

1.01

 disarm

1.00

 stalled

0.99

Activations Density 0.022%

the word "reform" and related concepts associated with governance and social change

No Comments

No Known Activations