INDEX

Explanations

information related to violent events and conflicts in various regions around the world

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

occurrences of verbs associated with casualties or displacement

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

0:0.05

1:0.04

2:0.13

3:0.03

4:0.04

5:0.10

6:0.09

7:0.13

8:0.06

9:0.04

10:0.10

11:0.15

Negative Logits

��

-1.54

 inception

-1.41

ciation

-1.39

 beginnings

-1.32

Byz

-1.32

 manufact

-1.31

 semantics

-1.31

 Chimera

-1.23

 archives

-1.23

odynamics

-1.22

POSITIVE LOGITS

pees

1.57

each

1.54

 unaccount

1.50

 apiece

1.47

amily

1.36

mort

1.34

ccording

1.33

aston

1.32

severe

1.30

%%

1.29

Activations Density 0.060%

information related to violent events and conflicts in various regions around the world

occurrences of verbs associated with casualties or displacement

No Comments

No Known Activations