INDEX

Explanations

content referring to legislative or political opposition

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.02

1:0.02

2:0.07

3:0.08

4:0.15

5:0.04

6:0.03

7:0.30

8:0.04

9:0.03

10:0.06

11:0.10

Negative Logits

�

-1.51

rg

-1.46

athered

-1.40

 Images

-1.38

aquin

-1.35

 Thumbnails

-1.34

hesda

-1.32

�

-1.31

ツ

-1.31

unity

-1.29

POSITIVE LOGITS

 curfew

1.51

llan

1.43

 agenda

1.43

Synopsis

1.37

 attempts

1.34

 paperwork

1.30

 agendas

1.30

 postp

1.30

 premie

1.29

 indefinitely

1.28

Activations Density 0.004%

content referring to legislative or political opposition

No Comments

No Known Activations