INDEX

Explanations

topics related to recognition and worthiness in various contexts

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

0:0.04

1:0.07

2:0.12

3:0.06

4:0.03

5:0.05

6:0.06

7:0.08

8:0.14

9:0.13

10:0.06

11:0.10

Negative Logits

 altern

-1.20

 Stores

-1.14

 reluct

-1.12

Gear

-1.11

 Panic

-1.08

Ves

-1.08

 wastes

-1.08

wind

-1.07

HW

-1.04

Kok

-1.02

POSITIVE LOGITS

thood

1.90

farious

1.43

ularity

1.36

 greatness

1.34

worthiness

1.29

ONY

1.29

daq

1.28

iership

1.27

ysical

1.27

 someday

1.27

Activations Density 0.003%

topics related to recognition and worthiness in various contexts

No Comments

No Known Activations