INDEX

Explanations

words related to political opinions and policies

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

support for various government policies and options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.03

2:0.14

3:0.09

4:0.06

5:0.10

6:0.02

7:0.02

8:0.20

9:0.13

10:0.05

11:0.02

Negative Logits

stress

-1.33

lance

-1.24

 pandemonium

-1.20

oche

-1.16

版

-1.15

��

-1.15

Sao

-1.15

 Bride

-1.14

ulhu

-1.12

orld

-1.11

POSITIVE LOGITS

 paternal

1.12

 pronouns

1.10

ilitarian

1.08

 filibuster

1.07

 Cosponsors

1.06

AFTA

1.05

 neutrality

1.05

tein

1.05

avorable

1.04

essim

1.04

Activations Density 0.010%

words related to political opinions and policies

support for various government policies and options

No Comments

No Known Activations