INDEX

Explanations

phrases that emphasize loudness and clarity in communication

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

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.02

2:0.07

3:0.15

4:0.02

5:0.04

6:0.10

7:0.16

8:0.05

9:0.07

10:0.07

11:0.18

Negative Logits

 Architects

-1.21

 Reincarn

-1.19

��極

-1.15

 Template

-1.14

pta

-1.13

onz

-1.12

��

-1.11

��

-1.09

��

-1.09

��

-1.08

POSITIVE LOGITS

mouth

1.32

 loud

1.29

 louder

1.27

 hyster

1.24

 emanating

1.17

 drown

1.13

bott

1.13

drive

1.12

(>

1.10

charge

1.10

Activations Density 0.008%

phrases that emphasize loudness and clarity in communication

No Comments

No Known Activations