INDEX

Explanations

locations or establishments

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

phrases related to historical events, political figures, and significant happenings

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

prepositional phrases indicating relationships or dependencies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.02

2:0.14

3:0.04

4:0.32

5:0.09

6:0.02

7:0.02

8:0.07

9:0.13

10:0.04

11:0.02

Negative Logits

jay

-1.65

itz

-1.61

voy

-1.55

brew

-1.54

ews

-1.54

blade

-1.52

ipolar

-1.52

cussion

-1.50

uter

-1.45

aunt

-1.43

POSITIVE LOGITS

 principles

1.51

UA

1.50

 fundamentals

1.50

 tenets

1.47

 foundations

1.43

 Satoshi

1.36

 premise

1.35

 foundation

1.35

 Revival

1.35

 dogma

1.32

Activations Density 0.006%

locations or establishments

phrases related to historical events, political figures, and significant happenings

prepositional phrases indicating relationships or dependencies

No Comments

No Known Activations