INDEX

Explanations

mentions of conflict and violence in geographical locations

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

occurrences of political turmoil and protests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

0:0.07

1:0.07

2:0.11

3:0.03

4:0.10

5:0.08

6:0.10

7:0.08

8:0.11

9:0.04

10:0.09

11:0.08

Negative Logits

 Disciple

-1.06

Stretch

-1.06

 Experiment

-1.04

 Philosophy

-1.01

��

-0.97

 Nerd

-0.97

ウス

-0.94

alogy

-0.94

~~~~

-0.93

 Journals

-0.92

POSITIVE LOGITS

 Nato

1.22

 WATCHED

1.19

 arrests

1.10

 favourable

1.10

FILE

1.09

ccording

1.09

 Britons

1.07

 ceasefire

1.06

 mortar

1.06

ESA

1.05

Activations Density 0.536%

mentions of conflict and violence in geographical locations

occurrences of political turmoil and protests

No Comments

No Known Activations