INDEX

Explanations

phrases related to monetary settlements and legal agreements

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

references to financial settlements and agreements

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

0:0.02

1:0.03

2:0.05

3:0.17

4:0.03

5:0.05

6:0.10

7:0.24

8:0.04

9:0.08

10:0.07

11:0.08

Negative Logits

 flares

-1.16

poke

-1.13

 Yugoslav

-1.11

POR

-1.09

AMA

-1.08

ビ

-1.06

 shoulder

-1.02

 skate

-1.02

Magikarp

-1.02

Reviewer

-1.02

POSITIVE LOGITS

nect

1.30

 Protocol

1.18

sett

1.14

aram

1.14

anwhile

1.11

ossier

1.11

amacare

1.06

reements

1.06

enture

1.06

rontal

1.06

Activations Density 0.007%

phrases related to monetary settlements and legal agreements

references to financial settlements and agreements

No Comments

No Known Activations