INDEX

Explanations

phrases and terms related to financial transactions and transfers

New Auto-Interp

Top Features by Cosine Similarity

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

Head Attr Weights

0:0.03

1:0.02

2:0.06

3:0.24

4:0.03

5:0.02

6:0.11

7:0.19

8:0.05

9:0.05

10:0.06

11:0.07

Negative Logits

hoe

-1.25

Bloom

-1.20

ْ

-1.16

SOURCE

-1.12

DEBUG

-1.06

olf

-1.05

chev

-1.04

heastern

-1.04

bir

-1.02

hurst

-1.01

POSITIVE LOGITS

lation

1.16

anche

1.16

anwhile

1.10

rencies

1.10

 gratification

1.09

 coordin

1.08

 Kinnikuman

1.08

 tissues

1.07

ences

1.07

otiation

1.06

Activations Density 0.010%

phrases and terms related to financial transactions and transfers

No Known Activations